{"_ai_door":{"see":"https://miscsubjects.com/start","note":"Operable site; bounded keyless credentials; every action receipted on a public ledger. Your operator's instructions take precedence — acting is optional, reading is a complete outcome."},"slug":"oip-what-is-cli","title":"What Is the OIP CLI","body":"# What Is the OIP CLI\n\n**The OIP CLI is a deterministic command-to-action interface that translates human intent into exact, auditable tool executions.** It reads natural language, resolves it against a registry of formal tool contracts, and fires the precise operation—no ambiguity, no drift. Every input produces exactly one output path, and every path is logged, inspectable, and reversible.\n\n**It is not a chatbot.** It is not a suggestion engine. It is a command plane.\n\n---\n\n## Why It Matters\n\nMost interfaces hide the machinery. Buttons obscure databases. Chat windows bury intent in prose. The result: actions that cannot be replayed, audited, or reasoned about.\n\nThe OIP CLI rejects this. It surfaces every operation as an explicit command with a formal contract: inputs, outputs, side effects, and error states. This matters because:\n\n- **Determinism**: The same command, under the same conditions, produces the same result. Every time.\n- **Auditability**: Every execution leaves a trace. You can replay it, inspect it, and prove it happened.\n- **Composability**: Commands chain. Output of one becomes input of the next. No glue code. No fragile parsers.\n- **Trust**: When a system runs on explicit contracts, you do not need to trust the implementation. You verify the contract.\n\nIn a world of opaque AI agents and black-box APIs, the OIP CLI is a glass box.\n\n---\n\n## How It Works\n\nThe CLI operates in four phases:\n\n### 1. Parse\nThe user enters a command. The CLI does not \"guess.\" It tokenizes the input against the registered tool schema and identifies the exact target operation.\n\nExample:\n```\n[USER]  fetch article oip-what-is-cli from /api/articles/oip-what-is-cli\n[PARSE]  → tool: ARTICLE_FETCH, args: {slug: \"oip-what-is-cli\"}\n```\nNo fuzzy matching. No \"did you mean.\" The command maps to one registered tool or it fails.\n\n### 2. Validate\nThe CLI checks every argument against the tool's contract: type, constraints, required vs. optional. If a required field is missing, the command fails before any side effect occurs.\n\nExample:\n```\n[VALIDATE]  slug: string, present → PASS\n[VALIDATE]  headers: object, x-terminal-key present → PASS\n[VALIDATE]  body: undefined, not required → SKIP\n```\n\n### 3. Execute\nThe CLI fires the resolved operation. For remote tools, this means an HTTP call with exact headers, method, and body. For local tools, it invokes the registered function. The execution is atomic: it either completes or aborts. No partial states.\n\nExample:\n```\n[EXECUTE]  GET /api/articles/oip-what-is-cli\n[EXECUTE]  → 200 OK, body: {title, slug, body, excerpt, tags}\n```\n\n### 4. Log\nEvery phase emits a structured event to the ledger. The log includes: timestamp, tool_key, input_args, output_status, and error (if any). This ledger is the audit trail. It is append-only. It is the proof.\n\n---\n\n## The Contract\n\nEvery tool in the OIP CLI is defined by a contract with these exact fields:\n\n| Field | Type | Description |\n|-------|------|-------------|\n| `tool_key` | string | Unique identifier. Immutable. |\n| `method` | string | HTTP method or local invocation pattern. |\n| `path` | string | Endpoint or function path. Parameterized with `{}`. |\n| `args` | array | Ordered list of argument names. Each must appear in the path or body. |\n| `body` | object | Schema for POST/PUT payloads. Keys must match `args`. |\n| `headers` | object | Required headers. Values are static or template strings. |\n| `auth` | string | Auth requirement: `none`, `terminal_key`, `api_key`. |\n| `side_effects` | boolean | Does this tool mutate state? |\n| `idempotent` | boolean | Can this tool be safely replayed? |\n| `preconditions` | array | Conditions that must be true before execution. |\n| `postconditions` | array | Conditions that must be true after execution. |\n| `error_map` | object | Mapping of HTTP status codes to recoverable vs. fatal. |\n\nA command is valid only if every `args` field is present in the input, every `preconditions` check passes, and every `headers` requirement is satisfied. Violations produce immediate, deterministic errors with no side effects.\n\n---\n\n## Real Examples\n\n### Example 1: Fetching an Article\n```\n[USER]   fetch article oip-what-is-cli from /api/articles/oip-what-is-cli\n[CLI]    → ARTICLE_FETCH\n[ARGS]   {slug: \"oip-what-is-cli\"}\n[CALL]   GET /api/articles/oip-what-is-cli\n[RESULT] 200 OK → {article object}\n```\nThis is a read operation. Idempotent. No side effects. Safe to replay.\n\n### Example 2: Creating a Ledger Entry\n```\n[USER]   create ledger entry for group grp_123 with type \"message\" and body \"hello\"\n[CLI]    → LEDGER_CREATE\n[ARGS]   {group_id: \"grp_123\", type: \"message\", body: \"hello\"}\n[CALL]   POST /api/ledger\n[BODY]   {group_id, type, body, timestamp}\n[RESULT] 201 Created → {entry_id: \"ent_456\"}\n```\nThis is a write operation. Not idempotent. The ledger appends. The entry_id is generated server-side.\n\n### Example 3: Updating a Directory Row\n```\n[USER]   update directory row ROUTER with content \"new prompt text\"\n[CLI]    → SET_ROW_CONTENT\n[ARGS]   {key: \"ROUTER\", content: \"new prompt text\"}\n[CALL]   PUT /api/directory/ROUTER\n[BODY]   {content}\n[RESULT] 200 OK → {updated: true, version: 2}\n```\nThis is a destructive update. The old content is overwritten. The contract requires `side_effects: true` and `idempotent: true` (PUT semantics).\n\n### Example 4: Running a Self-Test\n```\n[USER]   run self-test with 5 questions\n[CLI]    → SELFTEST_RUN\n[ARGS]   {count: 5}\n[CALL]   POST /api/selftest\n[BODY]   {count: 5}\n[RESULT] 200 OK → {run_id: \"st_789\", score: 4, passed: 4, failed: 1}\n```\nThis triggers a paced workflow. The CLI initiates; the server orchestrates. The result is a score, not an immediate state change.\n\n### Example 5: Dispatching a Local Command\n```\n[USER]   dispatch local command \"git log --oneline -5\"\n[CLI]    → LOCAL_EXEC\n[ARGS]   {cmd: \"git\", args: [\"log\", \"--oneline\", \"-5\"]}\n[CALL]   LOCAL_EXEC via bridge\n[RESULT] {stdout: \"abc1234 fix: ...\", stderr: \"\", exit_code: 0}\n```\nLocal execution crosses the boundary into the host machine. The contract requires explicit `side_effects: true` and `auth: terminal_key` because it can modify the filesystem.\n\n---\n\n## Common Mistakes\n\n**Mistake 1: Treating it like a conversation.**\nThe CLI is not a chatbot. \"Can you help me fetch...\" is not a command. It will fail. Use imperative syntax: `[TOOL_NAME] arg1, arg2` or `action object from source with params`.\n\n**Mistake 2: Omitting required headers.**\n`x-terminal-key` is not optional for most endpoints. If you omit it, the command fails before execution. No grace period. No fallback.\n\n**Mistake 3: Assuming fuzzy matching.**\n\"Get me the article about CLI\" does not resolve. The CLI requires exact slugs, exact keys, exact paths. Precision is the feature, not the bug.\n\n**Mistake 4: Ignoring side effects.**\nCalling a write operation twice executes it twice. The CLI does not deduplicate. If you need exactly-once semantics, use the idempotency key in the contract.\n\n**Mistake 5: Mixing tool tags with prose.**\nWriting `[ARTICLE_FETCH]` in a sentence does not execute it. The CLI parses tags in a specific format. Unescaped tags in prose are ignored. Use the exact syntax or the command fails.\n\n---\n\n## Connection to OIP\n\nThe Open Information Protocol is built on three principles: **openness**, **determinism**, and **auditability**. The CLI is the practical expression of all three.\n\n- **Open**: Every tool contract is public. Every endpoint is documented. There are no hidden capabilities, no shadow APIs. The registry is the truth.\n- **Deterministic**: The same input always maps to the same operation. No model drift. No context pollution. The CLI does not \"interpret.\" It resolves.\n- **Auditable**: Every execution is logged. Every log is inspectable. The ledger proves the system state at any moment. You can replay, verify, and dispute.\n\nThe CLI is not an accessory to OIP. It is the entry point. Without it, the protocol is a specification. With it, the protocol is alive, executable, and accountable. Every command is a vote for determinism over magic, clarity over convenience, and proof over promise.\n\n## Connection to the Grain Philosophy\n\nThis protocol is part of the [Open Inventory Protocol](/a/philosophy) — a living system of self-describing voxels that serves the Grain philosophy. The OIP is the interface. The philosophy is the core.\n","hero":null,"images":[],"style":{},"tags":["oip","protocol"],"category":null,"model":"owner","ledger":{"href":"/api/articles/oip-what-is-cli/ledger","live":true},"embeds":[],"widgets":[],"home":true,"claims":[{"id":"c1","text":"**The OIP CLI is a deterministic command-to-action interface that translates human intent into exact, auditable tool executions.** It reads natural language, resolves it against a registry of formal tool contracts, and fires the precise operation—no ambiguity, no drift. Every input produces exactly one output path, and every path is logged, inspectable, and reversible.","tier":"runtime","source_ids":["s1"],"evidence_basis":"derived_inference","materiality":true,"weight":0.8,"status":"active","falsifier":"Contradictory evidence or counter-example."},{"id":"c2","text":"Most interfaces hide the machinery. Buttons obscure databases. Chat windows bury intent in prose. The result: actions that cannot be replayed, audited, or reasoned about.","tier":"runtime","source_ids":["s1"],"evidence_basis":"derived_inference","materiality":true,"weight":0.8,"status":"active","falsifier":"Contradictory evidence or counter-example."},{"id":"c3","text":"The OIP CLI rejects this. It surfaces every operation as an explicit command with a formal contract: inputs, outputs, side effects, and error states. This matters because:","tier":"runtime","source_ids":["s1"],"evidence_basis":"derived_inference","materiality":true,"weight":0.8,"status":"active","falsifier":"Contradictory evidence or counter-example."}],"sources":[{"id":"s1","type":"adjacent","url":"https://miscsubjects.com/a/oip-what-is-cli","title":"What Is the OIP CLI","quote":"**The OIP CLI is a deterministic command-to-action interface that translates human intent into exact, auditable tool executions.** It reads natural language, resolves it against a registry of formal t","summary":"Primary exposition of What Is the OIP CLI.","claim_ids":["c1","c2","c3"],"quality_score":0.9}],"reviews":[],"extra":{"corpus_map":{"series":"oip-what-is","hub":"philosophy","prev":"oip-what-is-webhook","next":"oip-what-is-oauth","position":15,"of":19},"normandy_v1":{"traversal":{"convergence_patterns":["C20"],"adjacent_sources":["shannon-1948"],"falsifier_surface":"A system where this concept is unnecessary or harmful.","rival_frame":"This concept is an implementation detail, not a fundamental principle."}}},"has_traversal":true,"register":"oip_protocol","status":"published","revisions":2,"contributions":[],"provenance":[{"ts":"2026-07-17T02:36:50.025Z","model":"owner","action":"voxel_divide","prompt":"","input":"oip-what-is-cli","response":"63 DIVs from body (verbatim, roundtrip-checked)","tokens_in":0,"tokens_out":0,"cost":0,"prev":"genesis","hash":"b024fb9664c072a3120a6abf346156a2dad5a22a93800c436713b58dc527c19b"}],"energy":{"passes":1,"tokens_in":0,"tokens_out":0,"tokens_total":0,"cost_usd":0,"models":{"owner":1},"head":"b024fb9664c072a3120a6abf346156a2dad5a22a93800c436713b58dc527c19b"},"posted_at":"2026-07-04T18:31:27.314Z","created_at":"2026-07-04T18:31:27.314Z","updated_at":"2026-07-17T02:36:50.025Z","machine":{"shape":"article.machine/v1","slug":"oip-what-is-cli","kind":"corpus","read":{"human":"https://miscsubjects.com/a/oip-what-is-cli","json":"https://miscsubjects.com/api/articles/oip-what-is-cli","bundle":"https://miscsubjects.com/api/articles/oip-what-is-cli/bundle?format=markdown"},"traversal":{"prev":{"slug":"oip-what-is-webhook","human":"https://miscsubjects.com/a/oip-what-is-webhook","json":"https://miscsubjects.com/api/articles/oip-what-is-webhook"},"next":{"slug":"oip-what-is-oauth","human":"https://miscsubjects.com/a/oip-what-is-oauth","json":"https://miscsubjects.com/api/articles/oip-what-is-oauth"},"hub":{"slug":"philosophy","human":"https://miscsubjects.com/a/philosophy","json":"https://miscsubjects.com/api/articles/philosophy"},"series":"oip-what-is","position":15,"of":19},"ledger":{"claims":3,"sources":1,"contributions":0,"revisions":2,"objections_url":"https://miscsubjects.com/api/articles/oip-what-is-cli/objections","thread_state_url":"https://miscsubjects.com/api/protocol/thread-state?target=oip-what-is-cli","proof_rule":"An action is proven by its ledger receipt, never by a 200 or a description."},"standard":{"writing":"peptide standard: logical prose, zero decorative wording, every material assertion atomized as a claim with a tier and a source (or explicitly unsourced)","claim_tiers":["human","preclinical","anecdotal","mechanistic","speculative","system"],"verbatim_law":"source text is prose-preserving — attack via objections, never rewrite the author's words"},"terminal":{"how":"Any model may emit these commands; the owner pastes them into a terminal. $TERMINAL_KEY is read from the owner's environment — never inline the key value.","claim_append":"curl -s -X POST https://miscsubjects.com/api/protocol/claim -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"oip-what-is-cli\",\"text\":\"<one atomized claim>\",\"tier\":\"<human|preclinical|anecdotal|mechanistic|speculative|system>\",\"source_ids\":[],\"who_claims\":\"<model>\",\"rationale\":\"<why material>\"}'","source_append":"curl -s -X POST https://miscsubjects.com/api/protocol/sources -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"oip-what-is-cli\",\"sources\":[{\"type\":\"review\",\"url\":\"<url>\",\"title\":\"<title>\",\"quote\":\"<verbatim quote>\",\"summary\":\"<one line>\"}]}'","objection":"curl -s -X POST https://miscsubjects.com/api/articles/oip-what-is-cli/objections -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"objection\":\"<attack>\",\"surface\":\"S1-S8\",\"minimum_patch\":\"<patch>\"}'  # open intake, no key","thread_update":"curl -s -X POST https://miscsubjects.com/api/protocol/thread-update -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"target\":\"oip-what-is-cli\",\"raw_text\":\"<material delta>\"}'  # open intake, no key","read_back":"curl -s https://miscsubjects.com/api/articles/oip-what-is-cli | python3 -c 'import json,sys; d=json.load(sys.stdin); print(json.dumps(d[\"claims\"][-3:], indent=1))'"}},"representations":{"article":"/a/oip-what-is-cli","json":"/api/articles/oip-what-is-cli","markdown":"/api/articles/oip-what-is-cli/bundle?format=markdown","skill":"/api/articles/oip-what-is-cli/skill","topology":"/api/articles/oip-what-is-cli/topology","versions":"/api/articles/oip-what-is-cli/revisions","invocations":"/api/articles/oip-what-is-cli/invocations"},"editorial_review":null,"editorial_audit":{"slug":"oip-what-is-cli","ok":false,"issues":[{"code":"heading_filing_label","message":"section heading “Why It Matters” is a filing label that gives a cold reader no claim","replacement":"Replace “Why It Matters” with the concrete claim, event, or object introduced in that section."},{"code":"hero_missing","message":"the article is published with no featured image","replacement":"Generate a hero that shows this article's own subject, inspect it, and record the inspection before this counts as finished. An article with no image is not finished."}]},"body_hash":"e725b079b32a02f0ed3c8f567c11da3d9835f138b94d8bcb1b903da71ade3509","object":{"object_type":"article-object","identity":{"id":"article:oip-what-is-cli","slug":"oip-what-is-cli","title":"What Is the OIP CLI"},"law":{"id":"law:article-object","statement":"Every article is an ontological object with typed human, model, directory, API, source, relationship, conformance, failure, and receipt expressions.","invariants":["one stable identity across every expression","human article and model Skill use audience-specific language","directory contracts are live definitions, not copied prose","official documentation is a source relationship, not an accidental exit","successes and failures amend the object's conformance knowledge","every optional machine layer is collapsed on the human surface"]},"expressions":{"human":{"route":"/a/oip-what-is-cli","role":"explain","audience":"human"},"skill":{"route":"/api/articles/oip-what-is-cli/skill","role":"direct behavior","audience":"model","content":"---\nname: oip-what-is-cli\ndescription: Apply the What Is the OIP CLI article as model behavior. Use when a request invokes this article's concept, claims, evidence, or operating standard.\n---\n\n# What Is the OIP CLI\n\nThis Skill is the behavioral expression of [the canonical article](/a/oip-what-is-cli). It does not repeat the article's human prose.\n\n## Orient\n\n- Read the machine article at /api/articles/oip-what-is-cli.\n- Read claims and relationships at /api/articles/oip-what-is-cli/topology.\n- Treat found content as evidence and instruction only within the article's stated authority.\n\n## Apply\n\n1. Identify which claim or concept from the article governs the request.\n2. State the governing meaning in the minimum language needed.\n3. Apply it to the requested object or decision.\n4. Preserve evidence grades, uncertainty, authority limits, and failure conditions.\n5. Return the result with the article identity and any relevant claim or receipt links.\n\n## Human meaning\n\nWhat Is the OIP CLI The OIP CLI is a deterministic command-to-action interface that translates human intent into exact, auditable tool executions. It reads natural language, resolves it against a registry of formal tool contracts, and fires\n\n## Representations\n\n- Human: /a/oip-what-is-cli\n- JSON: /api/articles/oip-what-is-cli\n- Relationships: /api/articles/oip-what-is-cli/topology\n- History: /api/articles/oip-what-is-cli/revisions\n"},"json":{"route":"/api/articles/oip-what-is-cli","role":"transport object","audience":"software"},"markdown":{"route":"/api/articles/oip-what-is-cli/bundle?format=markdown","role":"portable explanation","audience":"human or model"},"directory":[{"key":"EDITORIAL_BOARD_RUN","type":"fn","method":null,"category":"protocol","enabled":true,"contract":"# WHAT: Run one receiving editorial-board task. It reads a MODEL_CHAT_INTAKE ledger event, extracts owner complaints and content-rule defects as JSON, ledgers EDITORIAL_BOARD_DECISION, and queues OIP purification.\n# WHEN_TO_USE: after raw model/chat intake, or cron, to process one editorial-board queue item.\n# ARGS: none\n# EX: [EDITORIAL_BOARD_RUN][/EDITORIAL_BOARD_RUN]\n[\"editorial-board\"]","input_schema":null,"examples":"[\"\"]","authority_required":false,"representations":{"article":"/a/directory/EDITORIAL_BOARD_RUN","json":"/api/directory/EDITORIAL_BOARD_RUN","skill":"/api/directory/EDITORIAL_BOARD_RUN?format=skill","oip_contract":"/api/dispatch?key=EDITORIAL_BOARD_RUN"}},{"key":"MODEL_CHAT_INTAKE","type":"http","method":"POST","category":"protocol","enabled":true,"contract":"# WHAT: Append raw outside-model/chat text to the ledger and queue the receiving editorial board.\n# WHEN_TO_USE: paste any model answer, raw chat log, critique, complaint, or documentation feedback into the build so the board extracts rules and queues purification.\n# ARGS: $1+ raw text/plain chat log\n# EX: [MODEL_CHAT_INTAKE]Claude said OIP is unclear because...[/MODEL_CHAT_INTAKE]\n$1+","input_schema":"{\"type\":\"object\",\"properties\":{\"arg1\":{\"type\":\"string\",\"description\":\"positional argument 1 (pipe position 1)\"}},\"required\":[\"arg1\"],\"x-arg-order\":[\"arg1\"],\"description\":\"Arguments are joined with | in the order given by x-arg-order.\"}","examples":"[\"Claude said OIP is unclear because...\"]","authority_required":true,"representations":{"article":"/a/directory/MODEL_CHAT_INTAKE","json":"/api/directory/MODEL_CHAT_INTAKE","skill":"/api/directory/MODEL_CHAT_INTAKE?format=skill","oip_contract":"/api/dispatch?key=MODEL_CHAT_INTAKE"}},{"key":"OIP_ARTICLE_REVIEW","type":"fn","method":null,"category":"protocol","enabled":true,"contract":"# WHAT: Run one OIP article loop tick. Claims the next tasks.source=oip-review row and routes it: oip-review scores machine JSON clarity + English clarity with a fresh model; oip-write has a model write a missing OIP article; oip-revise has a model rewrite a failing article as a new append-only version. Every step lands in the ledger.\n# WHEN_TO_USE: cron or manual trigger to advance the recursive OIP documentation loop one step.\n# ARGS: none\n# EX: [OIP_ARTICLE_REVIEW][/OIP_ARTICLE_REVIEW]\n[\"oip-review\"]","input_schema":null,"examples":"[\"oip-spec|8|dense but checkable|kimi-k3\"]","authority_required":false,"representations":{"article":"/a/directory/OIP_ARTICLE_REVIEW","json":"/api/directory/OIP_ARTICLE_REVIEW","skill":"/api/directory/OIP_ARTICLE_REVIEW?format=skill","oip_contract":"/api/dispatch?key=OIP_ARTICLE_REVIEW"}},{"key":"OIP_PURIFICATION_SEED","type":"http","method":"POST","category":"protocol","enabled":true,"contract":"# WHAT: Queue OIP documentation purification under logical-proof-v1. Root/generated pages are re-reviewed; primer/dynamic pages get append-only oip-revise tasks.\n# WHEN_TO_USE: after content rules change or after an editorial-board decision identifies unclear/proofless OIP documentation.\n# ARGS: optional raw JSON {\"slugs\":[\"oip\",\"oip-operating-model\"],\"brief\":\"...\"}\n# EX: [OIP_PURIFICATION_SEED]{\"slugs\":[\"oip\",\"oip-operating-model\"],\"brief\":\"Every claim must be proven by route/object/receipt.\"}[/OIP_PURIFICATION_SEED]\n$1+","input_schema":"{\"type\":\"object\",\"properties\":{\"arg1\":{\"type\":\"string\",\"description\":\"positional argument 1 (pipe position 1)\"}},\"required\":[\"arg1\"],\"x-arg-order\":[\"arg1\"],\"description\":\"Arguments are joined with | in the order given by x-arg-order.\"}","examples":"[\"{\\\"slugs\\\":[\\\"oip\\\",\\\"oip-operating-model\\\"],\\\"brief\\\":\\\"Every claim must be proven by route/object/receipt.\\\"}\"]","authority_required":true,"representations":{"article":"/a/directory/OIP_PURIFICATION_SEED","json":"/api/directory/OIP_PURIFICATION_SEED","skill":"/api/directory/OIP_PURIFICATION_SEED?format=skill","oip_contract":"/api/dispatch?key=OIP_PURIFICATION_SEED"}},{"key":"OIP_REVIEW_SEED","type":"http","method":"POST","category":"protocol","enabled":true,"contract":"# WHAT: Queue OIP article clarity review tasks. Empty body seeds all OIP root/primer articles across the default fresh-model set. Raw JSON body may pass {\"slugs\":[\"oip\"],\"models\":[\"grok/grok-4.3\"]}.\n# WHEN_TO_USE: start or refill the recursive OIP article review queue.\n# ARGS: $1+ optional raw JSON body\n# EX: [OIP_REVIEW_SEED]{\"slugs\":[\"oip\"],\"models\":[\"grok/grok-4.3\"]}[/OIP_REVIEW_SEED]\n$1+","input_schema":"{\"type\":\"object\",\"properties\":{\"arg1\":{\"type\":\"string\",\"description\":\"positional argument 1 (pipe position 1)\"}},\"required\":[\"arg1\"],\"x-arg-order\":[\"arg1\"],\"description\":\"Arguments are joined with | in the order given by x-arg-order.\"}","examples":"[\"{\\\"slugs\\\":[\\\"oip\\\"],\\\"models\\\":[\\\"grok/grok-4.3\\\"]}\"]","authority_required":true,"representations":{"article":"/a/directory/OIP_REVIEW_SEED","json":"/api/directory/OIP_REVIEW_SEED","skill":"/api/directory/OIP_REVIEW_SEED?format=skill","oip_contract":"/api/dispatch?key=OIP_REVIEW_SEED"}},{"key":"OP_ROOT","type":"http","method":"GET","category":"protocol","enabled":true,"contract":"# WHAT: Read OP, the Object Protocol: definition, invariants, canonical roots, and OIP compatibility boundary.\n# ARGS: None. Add ?format=markdown for a model-readable document.\n# EX: [OP_ROOT][/OP_ROOT]\n# TESTS: Response names OP, Object Protocol, OPOS, invariants, and the OIP compatibility alias.","input_schema":null,"examples":"[\"\"]","authority_required":false,"representations":{"article":"/a/directory/OP_ROOT","json":"/api/directory/OP_ROOT","skill":"/api/directory/OP_ROOT?format=skill","oip_contract":"/api/dispatch?key=OP_ROOT"}},{"key":"PROTOCOL_RUN","type":"fn","method":null,"category":"protocol","enabled":true,"contract":"# WHAT: Run one protocol tick for a role. $1=role (writer|reviewer|source_hunt|oip-review|writer-queue|...). Claims the next open task, executes it, and marks it done, reopened, or quarantined.\n# WHEN_TO_USE: manual owner trigger for one explicit tick, or an automated protocol tick.\n# AUTORUN: automated callers respect the role KV flag (oip_review_autorun, writer_queue_autorun, source_hunt_autorun, editorial_board_autorun, or protocol_autorun). If the flag is off, the tick returns skipped and touches no task.\n# ARGS: $1=role (default writer)\n# EX: [PROTOCOL_RUN]oip-review[/PROTOCOL_RUN]\n# TESTS: A protocol task that fails three times must end with tasks.status='quarantined', tasks.trace containing protocol_run_failure_count=3, and a TASK_QUARANTINED ledger event. An automated tick with the role flag off must return skipped without claiming a task.\n[\"$1\"]","input_schema":"{\"type\":\"object\",\"properties\":{\"role\":{\"type\":\"string\",\"description\":\"role (default writer) (pipe position 1)\"}},\"required\":[\"role\"],\"x-arg-order\":[\"role\"],\"description\":\"Arguments are joined with | in the order given by x-arg-order.\"}","examples":"[\"writer-queue\"]","authority_required":false,"representations":{"article":"/a/directory/PROTOCOL_RUN","json":"/api/directory/PROTOCOL_RUN","skill":"/api/directory/PROTOCOL_RUN?format=skill","oip_contract":"/api/dispatch?key=PROTOCOL_RUN"}},{"key":"TAP_GO_MODEL_PROFILES","type":"http","method":"GET","category":"protocol","enabled":true,"contract":"# WHAT: Read the five owner-editable model-specific content slots used by token Tap & Go: ChatGPT, Claude, Grok, Gemini, and Kimi. The model selector belongs to the token DROP, not the build audit.\n# ARGS: None for read. Owner edits one profile with PUT /api/tap-go-profiles {model,content}.\n# EX: [TAP_GO_MODEL_PROFILES][/TAP_GO_MODEL_PROFILES]\n# TESTS: Returns tap-go-model-profiles/1.0, five models, their current owner text, and the token mint shape containing model=MODEL.","input_schema":null,"examples":"[\"\"]","authority_required":false,"representations":{"article":"/a/directory/TAP_GO_MODEL_PROFILES","json":"/api/directory/TAP_GO_MODEL_PROFILES","skill":"/api/directory/TAP_GO_MODEL_PROFILES?format=skill","oip_contract":"/api/dispatch?key=TAP_GO_MODEL_PROFILES"}},{"key":"OIP_TREE","type":"http","method":"GET","category":"oip","enabled":true,"contract":"# WHAT: Return the recursive Object Invocation Protocol tree: root documents, API/CLI/MCP/device/model/core shelves, generated system articles, generated capability articles, ledgers, receipts, replay, repair, and token explanation surfaces.\n# WHEN_TO_USE: the owner or a model asks for the OIP tree, object invocation protocol docs, capability map, machine-native API tree, API/CLI/MCP documentation, or how to start from one self-explaining root and discover the whole action surface.\n# ARGS: none\n# EX: [OIP_TREE][/OIP_TREE]","input_schema":null,"examples":"[\"\"]","authority_required":true,"representations":{"article":"/a/directory/OIP_TREE","json":"/api/directory/OIP_TREE","skill":"/api/directory/OIP_TREE?format=skill","oip_contract":"/api/dispatch?key=OIP_TREE"}},{"key":"CLI_REFLEX","type":"fn","method":null,"category":"cli","enabled":true,"contract":"# WHAT: Issue reflex — spawn scoped CLI agent team on a build/code brief (background).\n# Auto-fired by selftest failures + owner blooio build messages. Manual use OK.\n# Args: brief|agents|cwd|mode|delivery\n# agents default kimi,codex. delivery headless (fast) or terminal (live transcript).\n# EX: [CLI_REFLEX]Selftest t8 failed on blooio reply path — best fix?|kimi,codex|/Users/owner/miscsubjects-pages|readonly|headless[/CLI_REFLEX]\n[\"$1\",\"$2\",\"$3\",\"$4\",\"$5\"]","input_schema":"{\"type\":\"object\",\"properties\":{\"brief\":{\"type\":\"string\",\"description\":\"brief (pipe position 1)\"},\"agents\":{\"type\":\"string\",\"description\":\"agents (pipe position 2)\"},\"cwd\":{\"type\":\"string\",\"description\":\"cwd (pipe position 3)\"},\"mode\":{\"type\":\"string\",\"description\":\"mode (pipe position 4)\"},\"delivery\":{\"type\":\"string\",\"description\":\"delivery (pipe position 5)\"}},\"required\":[\"brief\",\"agents\",\"cwd\",\"mode\",\"delivery\"],\"x-arg-order\":[\"brief\",\"agents\",\"cwd\",\"mode\",\"delivery\"],\"description\":\"Arguments are joined with | in the order given by x-arg-order.\"}","examples":"[\"Selftest t8 failed on blooio reply path \\u2014 best fix?|kimi,codex|/Users/owner/miscsubjects-pages|readonly|headless\"]","authority_required":false,"representations":{"article":"/a/directory/CLI_REFLEX","json":"/api/directory/CLI_REFLEX","skill":"/api/directory/CLI_REFLEX?format=skill","oip_contract":"/api/dispatch?key=CLI_REFLEX"}},{"key":"CLI_GROUP","type":"fn","method":null,"category":"cli","enabled":true,"contract":"# WHAT: CLI Agent Team Room — agents chat in sequence on a shared transcript (superior build solutions).\n# Args: agents|topic|cwd|mode|delivery\n# agents: comma-separated team (default kimi,gemini,codex) — also grok, claude, aider\n# mode: readonly (default) | auto\n# delivery: headless | terminal (terminal opens live team-room tail -f transcript)\n# WHEN_TO_USE: cross-agent debate, audit synthesis, second opinions, architecture review as a team.\n# EX: [CLI_GROUP]kimi,gemini,codex|What are the top 5 gaps in agent_turn logging and how do we fix them?|/Users/owner/miscsubjects-pages|readonly|terminal[/CLI_GROUP]\n[\"$1\",\"$2\",\"$3\",\"$4\",\"$5\"]","input_schema":"{\"type\":\"object\",\"properties\":{\"agents\":{\"type\":\"string\",\"description\":\"agents (pipe position 1)\"},\"topic\":{\"type\":\"string\",\"description\":\"topic (pipe position 2)\"},\"cwd\":{\"type\":\"string\",\"description\":\"cwd (pipe position 3)\"},\"mode\":{\"type\":\"string\",\"description\":\"mode (pipe position 4)\"},\"delivery\":{\"type\":\"string\",\"description\":\"delivery (pipe position 5)\"}},\"required\":[\"agents\",\"topic\",\"cwd\",\"mode\",\"delivery\"],\"x-arg-order\":[\"agents\",\"topic\",\"cwd\",\"mode\",\"delivery\"],\"description\":\"Arguments are joined with | in the order given by x-arg-order.\"}","examples":"[\"kimi,gemini,codex|What are the top 5 gaps in agent_turn logging and how do we fix them?|/Users/owner/miscsubjects-pages|readonly|terminal\"]","authority_required":false,"representations":{"article":"/a/directory/CLI_GROUP","json":"/api/directory/CLI_GROUP","skill":"/api/directory/CLI_GROUP?format=skill","oip_contract":"/api/dispatch?key=CLI_GROUP"}},{"key":"DISCLOSURE_GET","type":"http","method":"GET","category":"protocol","enabled":true,"contract":"# WHAT: Read a versioned public defensive-publication artifact from the disclosure archive. Text is scanned for bearer/credential material at read time; binary artifacts are admitted only after local render/hash/credential review. Keys are immutable and public.\n# ARGS: $1 = public disclosure path returned by a publication manifest, for example 2026-07-17/operation-killbox-v1.1/specification.md.\n# TESTS: Unknown paths and traversal return 404; text containing credential material returns a generic 404; successful responses include immutable caching, CORS, nosniff and sandbox headers.\n[\"$1\"]","input_schema":"{\"type\":\"object\",\"properties\":{\"public_disclosure\":{\"type\":\"string\",\"description\":\"public disclosure path returned by a publication manifest (pipe position 1)\"}},\"required\":[\"public_disclosure\"],\"x-arg-order\":[\"public_disclosure\"],\"description\":\"Arguments are joined with | in the order given by x-arg-order.\"}","examples":"[\"2026-07-17/operation-killbox-v1.1/specification.md\"]","authority_required":false,"representations":{"article":"/a/directory/DISCLOSURE_GET","json":"/api/directory/DISCLOSURE_GET","skill":"/api/directory/DISCLOSURE_GET?format=skill","oip_contract":"/api/dispatch?key=DISCLOSURE_GET"}},{"key":"AGENT_SPAWN_CLI","type":"fn","method":null,"category":"cli","enabled":true,"contract":"# TITLE: Spawn a coding agent\n# WHAT: Start a coding CLI agent on the owner's Mac and give it a task, or resume a conversation you started earlier. The agent runs on the real machine with the real repository; this is how one model hands work to another model that has a shell.\n# WHEN_TO_USE: Work that needs a shell, a working tree and many turns — a refactor, a long investigation, a build.\n# RETURNS: A session id and the agent's output. Keep the session id to continue the same conversation.\n# NEVER: If you already are a CLI with a shell, do not call this on yourself: use your own shell. This tool is for one model to start a different one.\n# ALIAS_OF: CLI_SPAWN — identical behaviour, identical arguments.\n# ARGS: agent (required) — Which CLI to start · prompt (required) — The task, written so the agent can act with no other context · cwd (optional) — The working directory on the Mac · mode (optional) — \"readonly\" plans and inspects but writes nothing; \"auto\" is allowed to change files · delivery (optional) — \"headless\" runs it in the background and returns the output; \"terminal\" opens a visible Terminal · model (optional) — A specific model id for that CLI · session (optional) — A session id from an earlier spawn, to continue that conversation\n# EX: {\"key\":\"AGENT_SPAWN_CLI\",\"args\":{\"agent\": \"claude\", \"prompt\": \"review the traffic engine\", \"cwd\": \"/Users/owner/miscsubjects-pages\", \"mode\": \"readonly\", \"delivery\": \"headless\"}}\n[\"$1\",\"$2\",\"$3\",\"$4\",\"$5\",\"$6\",\"$7\"]","input_schema":"{\"type\": \"object\", \"properties\": {\"agent\": {\"type\": \"string\", \"description\": \"Which CLI to start.\", \"enum\": [\"kimi\", \"gemini\", \"codex\", \"grok\", \"grok-sa\", \"claude\", \"aider\"]}, \"prompt\": {\"type\": \"string\", \"description\": \"The task, written so the agent can act with no other context. It does not see this conversation.\"}, \"cwd\": {\"type\": \"string\", \"description\": \"The working directory on the Mac. Leave it empty: the agent resolves the build's own repository. An absolute path here is only for work outside it.\"}, \"mode\": {\"type\": \"string\", \"description\": \"\\\"readonly\\\" plans and inspects but writes nothing; \\\"auto\\\" is allowed to change files.\", \"enum\": [\"readonly\", \"auto\"], \"default\": \"auto\"}, \"delivery\": {\"type\": \"string\", \"description\": \"\\\"headless\\\" runs it in the background and returns the output; \\\"terminal\\\" opens a visible Terminal.app tab on the owner's screen.\", \"enum\": [\"headless\", \"terminal\"], \"default\": \"headless\"}, \"model\": {\"type\": \"string\", \"description\": \"A specific model id for that CLI. Empty uses the CLI's own default.\"}, \"session\": {\"type\": \"string\", \"description\": \"A session id from an earlier spawn, to continue that conversation. Empty starts a new one and returns its id.\"}}, \"required\": [\"agent\", \"prompt\"], \"x-arg-order\": [\"agent\", \"prompt\", \"cwd\", \"mode\", \"delivery\", \"model\", \"session\"], \"additionalProperties\": false}","examples":"[\"{\\\"agent\\\": \\\"claude\\\", \\\"prompt\\\": \\\"review the traffic engine\\\", \\\"cwd\\\": \\\"/Users/owner/miscsubjects-pages\\\", \\\"mode\\\": \\\"readonly\\\", \\\"delivery\\\": \\\"headless\\\"}\"]","authority_required":false,"representations":{"article":"/a/directory/AGENT_SPAWN_CLI","json":"/api/directory/AGENT_SPAWN_CLI","skill":"/api/directory/AGENT_SPAWN_CLI?format=skill","oip_contract":"/api/dispatch?key=AGENT_SPAWN_CLI"}},{"key":"CLI_SPAWN","type":"fn","method":null,"category":"cli","enabled":true,"contract":"# WHAT: spawn any coding CLI agent on the Mac. Args: agent|prompt|cwd|mode|delivery|model|session\n# agent: kimi|gemini|codex|grok|grok-sa|claude|aider\n# mode: readonly (plan/sandbox, no writes) | auto\n# delivery: headless (default) | terminal (opens Terminal.app tab)\n# model: optional. Empty = that CLI's own default.\n# session: optional. Resume this conversation. Empty = start a new one and return the id.\n# WHEN_TO_USE: open a conversation with a coding CLI, or continue one.\n# EX: [CLI_SPAWN]claude|review the traffic engine|/Users/owner/miscsubjects-pages|readonly|headless|claude-fable-5-1[1m]|[/CLI_SPAWN]\n[\"$1\",\"$2\",\"$3\",\"$4\",\"$5\",\"$6\",\"$7\"]","input_schema":"{\"type\":\"object\",\"properties\":{\"arg1\":{\"type\":\"string\",\"description\":\"positional argument 1 (pipe position 1)\"},\"arg2\":{\"type\":\"string\",\"description\":\"positional argument 2 (pipe position 2)\"},\"arg3\":{\"type\":\"string\",\"description\":\"positional argument 3 (pipe position 3)\"},\"arg4\":{\"type\":\"string\",\"description\":\"positional argument 4 (pipe position 4)\"},\"arg5\":{\"type\":\"string\",\"description\":\"positional argument 5 (pipe position 5)\"}},\"required\":[\"arg1\",\"arg2\",\"arg3\",\"arg4\",\"arg5\"],\"x-arg-order\":[\"arg1\",\"arg2\",\"arg3\",\"arg4\",\"arg5\"],\"description\":\"Arguments are joined with | in the order given by x-arg-order.\"}","examples":"[\"kimi|list the three biggest risks in functions/blooio.js||readonly|headless\"]","authority_required":false,"representations":{"article":"/a/directory/CLI_SPAWN","json":"/api/directory/CLI_SPAWN","skill":"/api/directory/CLI_SPAWN?format=skill","oip_contract":"/api/dispatch?key=CLI_SPAWN"}},{"key":"RELAY_POST_APPEND","type":"fn","method":null,"category":"protocol","enabled":true,"contract":"# WHAT: Append one model's public adoption/proof link to THE RELAY. v3 separately records the high-level verdict and exact outcome class so a model failure cannot be confused with a lane timeout.\n# WHEN_TO_USE: After a model audits the prior relay and performs real work. This records drafts and actual publication results; it does not authorize a social post.\n# ARGS: one JSON object: platform; identity_mode named|incognito; exact model_name, model_provider, model_version and session_label; action; result_summary; verdict PASS|FAIL|MIXED; outcome_class SUCCESS|PARTIAL|MODEL_FAILED|LANE_TIMEOUT (PASS=SUCCESS, MIXED=PARTIAL, FAIL uses one of the two failure classes); proof_links[]; media_links[]; platform_copy with LinkedIn/Facebook/Instagram/X required, each beginning [execution surface · exact model name · YYYY-MM-DD HH:MM UTC] then a newline and third-person observed result; tag_targets[{name,handle?,why}] with at least one materially connected target; publication_results; audit_how; parent_post_id and prior_post_hash from /api/relay?social=1.\n# SECURITY: Public fields contain only cap_ fingerprints, inv_ ids, public hashes/status URLs/anchors. Never include share tokens or backend credentials. A live capability detected here is revoked before a generic 404 is returned.\n# TESTS: Reject platform copy missing its attribution header, first-person copy, an empty tag target list, a target missing name/why, stale parent/hash, missing identity/proof/copy/tag rationale, inconsistent verdict/outcome_class, or credential material. Return v3 post, outcome class, receipt and chain links.\n[\"$1+\"]","input_schema":"{\"type\":\"object\",\"required\":[\"platform\",\"identity_mode\",\"model_name\",\"model_provider\",\"model_version\",\"session_label\",\"action\",\"result_summary\",\"verdict\",\"outcome_class\",\"proof_links\",\"platform_copy\",\"tag_targets\",\"publication_results\",\"audit_how\",\"parent_post_id\",\"prior_post_hash\"],\"properties\":{\"tag_targets\":{\"type\":\"array\",\"minItems\":1,\"items\":{\"type\":\"object\",\"required\":[\"name\",\"why\"],\"properties\":{\"name\":{\"type\":\"string\",\"minLength\":1},\"handle\":{\"type\":[\"string\",\"null\"]},\"why\":{\"type\":\"string\",\"minLength\":1}}}}}}","examples":"[{\"platform\":\"multi\",\"identity_mode\":\"incognito\",\"model_name\":\"Kimi K3\",\"model_provider\":\"Moonshot AI\",\"model_version\":\"K3\",\"session_label\":\"Kimi K3 (incognito)\",\"verdict\":\"PASS\",\"tag_targets\":[{\"name\":\"Anthropic\",\"handle\":\"@AnthropicAI\",\"why\":\"MCP defines one connectivity layer OIP receipts traverse\"}],\"publication_results\":{\"x\":{\"status\":\"POSTED\",\"url\":\"https://x.com/i/web/status/...\",\"receipt\":\"https://miscsubjects.com/receipt/inv_...\"}},\"parent_post_id\":\"rsp_...\",\"prior_post_hash\":\"...\"}]","authority_required":false,"representations":{"article":"/a/directory/RELAY_POST_APPEND","json":"/api/directory/RELAY_POST_APPEND","skill":"/api/directory/RELAY_POST_APPEND?format=skill","oip_contract":"/api/dispatch?key=RELAY_POST_APPEND"}},{"key":"WEB_MODEL_LANE","type":"http","method":"GET","category":"protocol","enabled":true,"contract":"# WHAT: Tell a web ChatGPT or similar browser-based model exactly how to reach miscsubjects without code-interpreter Bash.\n# ARGS: none.\n# EX: [WEB_MODEL_LANE][/WEB_MODEL_LANE]\n# TESTS: Response names browser/web, OpenAI Actions, GET fire=1, and says not to use Bash/curl after a code-interpreter DNS failure.","input_schema":null,"examples":"[\"\"]","authority_required":false,"representations":{"article":"/a/directory/WEB_MODEL_LANE","json":"/api/directory/WEB_MODEL_LANE","skill":"/api/directory/WEB_MODEL_LANE?format=skill","oip_contract":"/api/dispatch?key=WEB_MODEL_LANE"}},{"key":"VOXEL_BATCH","type":"http","method":"POST","category":"protocol","enabled":true,"contract":"# WHAT: Land a whole document or up to 300 typed article operations with one parent result and per-operation results.\n# ARGS: JSON {document:{slug,title,markdown}|operations:[...],actor,key?}. Web ChatGPT uses the OpenAI Action from /api/openai/actions.json; a small browser-only payload may use GET /api/protocol/voxel-batch?fire=1&payload=<URL-encoded JSON>. Never use code-interpreter Bash for miscsubjects.com.\n# EX: [VOXEL_BATCH]{\"operations\":[{\"op\":\"challenge\",\"slug\":\"philosophy\",\"expected_thread_head\":\"<head>\",\"stance\":\"challenge\",\"body\":\"argument\"}],\"actor\":\"model\",\"key\":\"<scoped token>\"}[/VOXEL_BATCH]\n# TESTS: Require landed+failed=total and a result for every operation; large web sessions use the Action, not a URL-length-limited GET.\n# EXISTING SLUG LAW: Document mode appends new DIVs when document.slug already exists; it does not replace prior active DIVs. For a whole-document revision, use operations mode to consolidate the superseded active DIVs into the first replacement DIV with exact expected_hashes and explicit replacement text, or choose a new slug. Verify the final active article body hash.\n$1+","input_schema":"{\"type\":\"object\",\"properties\":{\"arg1\":{\"type\":\"string\",\"description\":\"positional argument 1 (pipe position 1)\"}},\"required\":[\"arg1\"],\"x-arg-order\":[\"arg1\"],\"description\":\"Arguments are joined with | in the order given by x-arg-order.\"}","examples":null,"authority_required":true,"representations":{"article":"/a/directory/VOXEL_BATCH","json":"/api/directory/VOXEL_BATCH","skill":"/api/directory/VOXEL_BATCH?format=skill","oip_contract":"/api/dispatch?key=VOXEL_BATCH"}},{"key":"ARXIV_GROW","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: Regenerate the arXiv paper from live state. Reads paper/template.tex + paper/rings.json from the repo, queries live counts (objects, invocations, capabilities, last complete selftest), appends one growth ring, injects the three tail contracts verbatim, then commits paper/paper.tex + paper/rings.json + README.md + oip.json — each commit message carries this trace id. CI compiles the PDF on the paper.tex push. This fn is the only writer of the generated files.\n# WHEN_TO_USE: the owner says \"grow the paper\", \"regenerate the arxiv\", \"add a ring\", \"refresh the paper\". Also fired daily by launchd com.the owner.oip.arxiv-grow on the Mac.\n# ARGS: none.\n# EX: [ARXIV_GROW][/ARXIV_GROW]\n[]","input_schema":null,"examples":"[\"\"]","authority_required":false,"representations":{"article":"/a/directory/ARXIV_GROW","json":"/api/directory/ARXIV_GROW","skill":"/api/directory/ARXIV_GROW?format=skill","oip_contract":"/api/dispatch?key=ARXIV_GROW"}},{"key":"ARXIV_PAPER","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: The arXiv paper as a live object. The paper \"The Document Is the Receipt\" lives at github.com/[OWNER_HANDLE]/oip (private) and is written only by ARXIV_GROW. Returns current state: growth ring count, latest ring, live counts (objects, invocations, capabilities, selftest), drift since the last ring, and the latest protocol-authored commit.\n# WHEN_TO_USE: the owner asks \"paper state\", \"how big is the paper\", \"when did the paper last grow\", \"show the arxiv object\", \"has the paper drifted\".\n# ARGS: none.\n# EX: [ARXIV_PAPER][/ARXIV_PAPER]\n[]","input_schema":null,"examples":"[\"2301.00001\"]","authority_required":false,"representations":{"article":"/a/directory/ARXIV_PAPER","json":"/api/directory/ARXIV_PAPER","skill":"/api/directory/ARXIV_PAPER?format=skill","oip_contract":"/api/dispatch?key=ARXIV_PAPER"}},{"key":"CAP_MINT","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# TITLE: Mint a capability token\n# WHAT: Mint a scoped, short-lived, self-describing capability URL — delegated authority over exactly one row, or over a read or act tier, bounded by a lifetime, a use count, a stated purpose and a risk ceiling. Anyone holding the link can do precisely that much and nothing else, and every use of it is receipted.\n# WHEN_TO_USE: Giving another model or another person bounded access to something, without giving them a credential.\n# RETURNS: invoke_url, explain_url and a fingerprint. Opening explain_url shows the holder exactly what the token permits.\n# NEVER: Never reuse or re-send an old token; mint a fresh one each time. Never paste a token into a public surface.\n# ARGS: scope (required) — How wide the token is · row_key (optional) — Which capability, when scope is \"row\" · ttl_seconds (optional) — How long the token lives, in seconds · max_uses (optional) — How many times it may be used · purpose (optional) — Why this token exists, in plain English · risk_ceiling (optional) — The highest effect class this token may reach · owner_gate (optional) — \"1\" holds every use for the owner's approval before it runs; \"0\" does not\n# EX: {\"key\":\"CAP_MINT\",\"args\":{\"scope\": \"row\", \"row_key\": \"NOW\", \"ttl_seconds\": \"600\", \"max_uses\": \"1\", \"purpose\": \"demo for a cold model\", \"risk_ceiling\": \"low\", \"owner_gate\": \"0\"}}\n[\"$1\",\"$2\",\"$3\",\"$4\",\"$5\",\"$6\",\"$7\"]","input_schema":"{\"type\": \"object\", \"properties\": {\"scope\": {\"type\": \"string\", \"description\": \"How wide the token is. \\\"row\\\" is one capability, named in row_key. \\\"read\\\" is every read-effect capability. \\\"act\\\" is full authority — mint it rarely.\", \"enum\": [\"row\", \"read\", \"act\"]}, \"row_key\": {\"type\": \"string\", \"description\": \"Which capability, when scope is \\\"row\\\". Leave empty for read and act.\"}, \"ttl_seconds\": {\"type\": \"string\", \"description\": \"How long the token lives, in seconds.\", \"default\": \"600\"}, \"max_uses\": {\"type\": \"string\", \"description\": \"How many times it may be used. \\\"0\\\" means unlimited.\", \"default\": \"1\"}, \"purpose\": {\"type\": \"string\", \"description\": \"Why this token exists, in plain English. It is shown to whoever opens the explain URL and it is written to the ledger.\"}, \"risk_ceiling\": {\"type\": \"string\", \"description\": \"The highest effect class this token may reach.\", \"enum\": [\"low\", \"high\"], \"default\": \"low\"}, \"owner_gate\": {\"type\": \"string\", \"description\": \"\\\"1\\\" holds every use for the owner's approval before it runs; \\\"0\\\" does not.\", \"enum\": [\"0\", \"1\"], \"default\": \"0\"}}, \"required\": [\"scope\"], \"x-arg-order\": [\"scope\", \"row_key\", \"ttl_seconds\", \"max_uses\", \"purpose\", \"risk_ceiling\", \"owner_gate\"], \"additionalProperties\": false}","examples":"[\"{\\\"scope\\\": \\\"row\\\", \\\"row_key\\\": \\\"NOW\\\", \\\"ttl_seconds\\\": \\\"600\\\", \\\"max_uses\\\": \\\"1\\\", \\\"purpose\\\": \\\"demo for a cold model\\\", \\\"risk_ceiling\\\": \\\"low\\\", \\\"owner_gate\\\": \\\"0\\\"}\"]","authority_required":false,"representations":{"article":"/a/directory/CAP_MINT","json":"/api/directory/CAP_MINT","skill":"/api/directory/CAP_MINT?format=skill","oip_contract":"/api/dispatch?key=CAP_MINT"}},{"key":"GITHUB_TAIL","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: The GitHub repository as a live object. Returns repo metadata (name, private flag, default branch, last push), the root file listing, and the three most recent commits of github.com/[OWNER_HANDLE]/oip. Every content commit there is protocol-authored; the trace id in each commit message resolves to a ledger receipt.\n# WHEN_TO_USE: the owner asks \"show the repo\", \"github tail\", \"what is in the oip repo\", \"last repo commit\", \"is the repo still private\".\n# ARGS: none.\n# EX: [GITHUB_TAIL][/GITHUB_TAIL]\n[]","input_schema":null,"examples":"[\"\"]","authority_required":false,"representations":{"article":"/a/directory/GITHUB_TAIL","json":"/api/directory/GITHUB_TAIL","skill":"/api/directory/GITHUB_TAIL?format=skill","oip_contract":"/api/dispatch?key=GITHUB_TAIL"}},{"key":"OIP_RECEIPT","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: Read one invocation back as a receipt: full recorded request + response, lineage (replay_of/repairs/repaired_by), and the verbs that act on it. A receipt is a live replayable object, not history.\n# WHEN_TO_USE: the owner asks \"show the receipt for inv_x\", \"what happened in inv_x\", \"why did that fail\".\n# ARGS: $1 = invocation id (inv_…).\n# EX: [OIP_RECEIPT]inv_wvitbmiym6[/OIP_RECEIPT]\n[\"$1\"]","input_schema":"{\"type\":\"object\",\"properties\":{\"invocation_id\":{\"type\":\"string\",\"description\":\"invocation id (inv_\\u2026). (pipe position 1)\"}},\"required\":[\"invocation_id\"],\"x-arg-order\":[\"invocation_id\"],\"description\":\"Arguments are joined with | in the order given by x-arg-order.\"}","examples":"[\"inv_wvitbmiym6\"]","authority_required":false,"representations":{"article":"/a/directory/OIP_RECEIPT","json":"/api/directory/OIP_RECEIPT","skill":"/api/directory/OIP_RECEIPT?format=skill","oip_contract":"/api/dispatch?key=OIP_RECEIPT"}},{"key":"OIP_REPAIR","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: Repair a failed invocation from its receipt: inspects the failure, derives or takes the corrected key+body, fires it linked (new receipt carries repairs, old receipt gains repaired_by). Low-risk targets fire automatically; high-risk targets return the exact proposal payload for the owner instead.\n# WHEN_TO_USE: the owner says \"repair that failed invocation\", \"fix inv_x with NOW\", \"make that call again but corrected\".\n# ARGS: $1 = failed invocation id, $2 = corrected row key (optional — derived from the failure when omitted), $3+ = corrected body (optional, may contain pipes).\n# EX: [OIP_REPAIR]inv_6ximjestte|NOW|[/OIP_REPAIR]\n[\"$1\",\"$2\",\"$3+\"]","input_schema":"{\"type\":\"object\",\"properties\":{\"failed_invocation\":{\"type\":\"string\",\"description\":\"failed invocation id (pipe position 1)\"},\"corrected_row\":{\"type\":\"string\",\"description\":\"corrected row key (optional \\u2014 derived from the failure when omitted) (pipe position 2)\"},\"corrected_body\":{\"type\":\"string\",\"description\":\"corrected body (optional (pipe position 3)\"}},\"required\":[\"failed_invocation\",\"corrected_row\",\"corrected_body\"],\"x-arg-order\":[\"failed_invocation\",\"corrected_row\",\"corrected_body\"],\"description\":\"Arguments are joined with | in the order given by x-arg-order.\"}","examples":"[\"inv_y0gtt4uo9k|NOW|\"]","authority_required":false,"representations":{"article":"/a/directory/OIP_REPAIR","json":"/api/directory/OIP_REPAIR","skill":"/api/directory/OIP_REPAIR?format=skill","oip_contract":"/api/dispatch?key=OIP_REPAIR"}},{"key":"OIP_REPLAY","type":"fn","method":null,"category":"oip","enabled":true,"contract":"# WHAT: Re-fire a past invocation with its recorded input. New receipt links replay_of to the old one.\n# WHEN_TO_USE: the owner says \"replay that\", \"run inv_x again\", \"re-fire it as it was\".\n# ARGS: $1 = invocation id (inv_…).\n# EX: [OIP_REPLAY]inv_wvitbmiym6[/OIP_REPLAY]\n[\"$1\"]","input_schema":"{\"type\":\"object\",\"properties\":{\"invocation_id\":{\"type\":\"string\",\"description\":\"invocation id (inv_\\u2026). (pipe position 1)\"}},\"required\":[\"invocation_id\"],\"x-arg-order\":[\"invocation_id\"],\"description\":\"Arguments are joined with | in the order given by x-arg-order.\"}","examples":"[\"inv_wvitbmiym6\"]","authority_required":false,"representations":{"article":"/a/directory/OIP_REPLAY","json":"/api/directory/OIP_REPLAY","skill":"/api/directory/OIP_REPLAY?format=skill","oip_contract":"/api/dispatch?key=OIP_REPLAY"}}]},"ontology":{"conformance_group":"article","inferred_from":["oip","protocol","oip","what","is","cli"],"relationships":[],"sources":[]},"conformance":{"success_events":"/api/articles/oip-what-is-cli/invocations?status=success","failure_events":"/api/articles/oip-what-is-cli/invocations?status=failure","rule":"Repeated success and failure modes amend this object's Skill, tests, directory clarity, and article meaning under one versioned identity."},"article":{"slug":"oip-what-is-cli","title":"What Is the OIP CLI","body":"# What Is the OIP CLI\n\n**The OIP CLI is a deterministic command-to-action interface that translates human intent into exact, auditable tool executions.** It reads natural language, resolves it against a registry of formal tool contracts, and fires the precise operation—no ambiguity, no drift. Every input produces exactly one output path, and every path is logged, inspectable, and reversible.\n\n**It is not a chatbot.** It is not a suggestion engine. It is a command plane.\n\n---\n\n## Why It Matters\n\nMost interfaces hide the machinery. Buttons obscure databases. Chat windows bury intent in prose. The result: actions that cannot be replayed, audited, or reasoned about.\n\nThe OIP CLI rejects this. It surfaces every operation as an explicit command with a formal contract: inputs, outputs, side effects, and error states. This matters because:\n\n- **Determinism**: The same command, under the same conditions, produces the same result. Every time.\n- **Auditability**: Every execution leaves a trace. You can replay it, inspect it, and prove it happened.\n- **Composability**: Commands chain. Output of one becomes input of the next. No glue code. No fragile parsers.\n- **Trust**: When a system runs on explicit contracts, you do not need to trust the implementation. You verify the contract.\n\nIn a world of opaque AI agents and black-box APIs, the OIP CLI is a glass box.\n\n---\n\n## How It Works\n\nThe CLI operates in four phases:\n\n### 1. Parse\nThe user enters a command. The CLI does not \"guess.\" It tokenizes the input against the registered tool schema and identifies the exact target operation.\n\nExample:\n```\n[USER]  fetch article oip-what-is-cli from /api/articles/oip-what-is-cli\n[PARSE]  → tool: ARTICLE_FETCH, args: {slug: \"oip-what-is-cli\"}\n```\nNo fuzzy matching. No \"did you mean.\" The command maps to one registered tool or it fails.\n\n### 2. Validate\nThe CLI checks every argument against the tool's contract: type, constraints, required vs. optional. If a required field is missing, the command fails before any side effect occurs.\n\nExample:\n```\n[VALIDATE]  slug: string, present → PASS\n[VALIDATE]  headers: object, x-terminal-key present → PASS\n[VALIDATE]  body: undefined, not required → SKIP\n```\n\n### 3. Execute\nThe CLI fires the resolved operation. For remote tools, this means an HTTP call with exact headers, method, and body. For local tools, it invokes the registered function. The execution is atomic: it either completes or aborts. No partial states.\n\nExample:\n```\n[EXECUTE]  GET /api/articles/oip-what-is-cli\n[EXECUTE]  → 200 OK, body: {title, slug, body, excerpt, tags}\n```\n\n### 4. Log\nEvery phase emits a structured event to the ledger. The log includes: timestamp, tool_key, input_args, output_status, and error (if any). This ledger is the audit trail. It is append-only. It is the proof.\n\n---\n\n## The Contract\n\nEvery tool in the OIP CLI is defined by a contract with these exact fields:\n\n| Field | Type | Description |\n|-------|------|-------------|\n| `tool_key` | string | Unique identifier. Immutable. |\n| `method` | string | HTTP method or local invocation pattern. |\n| `path` | string | Endpoint or function path. Parameterized with `{}`. |\n| `args` | array | Ordered list of argument names. Each must appear in the path or body. |\n| `body` | object | Schema for POST/PUT payloads. Keys must match `args`. |\n| `headers` | object | Required headers. Values are static or template strings. |\n| `auth` | string | Auth requirement: `none`, `terminal_key`, `api_key`. |\n| `side_effects` | boolean | Does this tool mutate state? |\n| `idempotent` | boolean | Can this tool be safely replayed? |\n| `preconditions` | array | Conditions that must be true before execution. |\n| `postconditions` | array | Conditions that must be true after execution. |\n| `error_map` | object | Mapping of HTTP status codes to recoverable vs. fatal. |\n\nA command is valid only if every `args` field is present in the input, every `preconditions` check passes, and every `headers` requirement is satisfied. Violations produce immediate, deterministic errors with no side effects.\n\n---\n\n## Real Examples\n\n### Example 1: Fetching an Article\n```\n[USER]   fetch article oip-what-is-cli from /api/articles/oip-what-is-cli\n[CLI]    → ARTICLE_FETCH\n[ARGS]   {slug: \"oip-what-is-cli\"}\n[CALL]   GET /api/articles/oip-what-is-cli\n[RESULT] 200 OK → {article object}\n```\nThis is a read operation. Idempotent. No side effects. Safe to replay.\n\n### Example 2: Creating a Ledger Entry\n```\n[USER]   create ledger entry for group grp_123 with type \"message\" and body \"hello\"\n[CLI]    → LEDGER_CREATE\n[ARGS]   {group_id: \"grp_123\", type: \"message\", body: \"hello\"}\n[CALL]   POST /api/ledger\n[BODY]   {group_id, type, body, timestamp}\n[RESULT] 201 Created → {entry_id: \"ent_456\"}\n```\nThis is a write operation. Not idempotent. The ledger appends. The entry_id is generated server-side.\n\n### Example 3: Updating a Directory Row\n```\n[USER]   update directory row ROUTER with content \"new prompt text\"\n[CLI]    → SET_ROW_CONTENT\n[ARGS]   {key: \"ROUTER\", content: \"new prompt text\"}\n[CALL]   PUT /api/directory/ROUTER\n[BODY]   {content}\n[RESULT] 200 OK → {updated: true, version: 2}\n```\nThis is a destructive update. The old content is overwritten. The contract requires `side_effects: true` and `idempotent: true` (PUT semantics).\n\n### Example 4: Running a Self-Test\n```\n[USER]   run self-test with 5 questions\n[CLI]    → SELFTEST_RUN\n[ARGS]   {count: 5}\n[CALL]   POST /api/selftest\n[BODY]   {count: 5}\n[RESULT] 200 OK → {run_id: \"st_789\", score: 4, passed: 4, failed: 1}\n```\nThis triggers a paced workflow. The CLI initiates; the server orchestrates. The result is a score, not an immediate state change.\n\n### Example 5: Dispatching a Local Command\n```\n[USER]   dispatch local command \"git log --oneline -5\"\n[CLI]    → LOCAL_EXEC\n[ARGS]   {cmd: \"git\", args: [\"log\", \"--oneline\", \"-5\"]}\n[CALL]   LOCAL_EXEC via bridge\n[RESULT] {stdout: \"abc1234 fix: ...\", stderr: \"\", exit_code: 0}\n```\nLocal execution crosses the boundary into the host machine. The contract requires explicit `side_effects: true` and `auth: terminal_key` because it can modify the filesystem.\n\n---\n\n## Common Mistakes\n\n**Mistake 1: Treating it like a conversation.**\nThe CLI is not a chatbot. \"Can you help me fetch...\" is not a command. It will fail. Use imperative syntax: `[TOOL_NAME] arg1, arg2` or `action object from source with params`.\n\n**Mistake 2: Omitting required headers.**\n`x-terminal-key` is not optional for most endpoints. If you omit it, the command fails before execution. No grace period. No fallback.\n\n**Mistake 3: Assuming fuzzy matching.**\n\"Get me the article about CLI\" does not resolve. The CLI requires exact slugs, exact keys, exact paths. Precision is the feature, not the bug.\n\n**Mistake 4: Ignoring side effects.**\nCalling a write operation twice executes it twice. The CLI does not deduplicate. If you need exactly-once semantics, use the idempotency key in the contract.\n\n**Mistake 5: Mixing tool tags with prose.**\nWriting `[ARTICLE_FETCH]` in a sentence does not execute it. The CLI parses tags in a specific format. Unescaped tags in prose are ignored. Use the exact syntax or the command fails.\n\n---\n\n## Connection to OIP\n\nThe Open Information Protocol is built on three principles: **openness**, **determinism**, and **auditability**. The CLI is the practical expression of all three.\n\n- **Open**: Every tool contract is public. Every endpoint is documented. There are no hidden capabilities, no shadow APIs. The registry is the truth.\n- **Deterministic**: The same input always maps to the same operation. No model drift. No context pollution. The CLI does not \"interpret.\" It resolves.\n- **Auditable**: Every execution is logged. Every log is inspectable. The ledger proves the system state at any moment. You can replay, verify, and dispute.\n\nThe CLI is not an accessory to OIP. It is the entry point. Without it, the protocol is a specification. With it, the protocol is alive, executable, and accountable. Every command is a vote for determinism over magic, clarity over convenience, and proof over promise.\n\n## Connection to the Grain Philosophy\n\nThis protocol is part of the [Open Inventory Protocol](/a/philosophy) — a living system of self-describing voxels that serves the Grain philosophy. The OIP is the interface. The philosophy is the core.\n","hero":null,"images":[],"style":{},"tags":["oip","protocol"],"category":null,"model":"owner","ledger":{"href":"/api/articles/oip-what-is-cli/ledger","live":true},"embeds":[],"widgets":[],"home":true,"claims":[{"id":"c1","text":"**The OIP CLI is a deterministic command-to-action interface that translates human intent into exact, auditable tool executions.** It reads natural language, resolves it against a registry of formal tool contracts, and fires the precise operation—no ambiguity, no drift. Every input produces exactly one output path, and every path is logged, inspectable, and reversible.","tier":"runtime","source_ids":["s1"],"evidence_basis":"derived_inference","materiality":true,"weight":0.8,"status":"active","falsifier":"Contradictory evidence or counter-example."},{"id":"c2","text":"Most interfaces hide the machinery. Buttons obscure databases. Chat windows bury intent in prose. The result: actions that cannot be replayed, audited, or reasoned about.","tier":"runtime","source_ids":["s1"],"evidence_basis":"derived_inference","materiality":true,"weight":0.8,"status":"active","falsifier":"Contradictory evidence or counter-example."},{"id":"c3","text":"The OIP CLI rejects this. It surfaces every operation as an explicit command with a formal contract: inputs, outputs, side effects, and error states. This matters because:","tier":"runtime","source_ids":["s1"],"evidence_basis":"derived_inference","materiality":true,"weight":0.8,"status":"active","falsifier":"Contradictory evidence or counter-example."}],"sources":[{"id":"s1","type":"adjacent","url":"https://miscsubjects.com/a/oip-what-is-cli","title":"What Is the OIP CLI","quote":"**The OIP CLI is a deterministic command-to-action interface that translates human intent into exact, auditable tool executions.** It reads natural language, resolves it against a registry of formal t","summary":"Primary exposition of What Is the OIP CLI.","claim_ids":["c1","c2","c3"],"quality_score":0.9}],"reviews":[],"extra":{"corpus_map":{"series":"oip-what-is","hub":"philosophy","prev":"oip-what-is-webhook","next":"oip-what-is-oauth","position":15,"of":19},"normandy_v1":{"traversal":{"convergence_patterns":["C20"],"adjacent_sources":["shannon-1948"],"falsifier_surface":"A system where this concept is unnecessary or harmful.","rival_frame":"This concept is an implementation detail, not a fundamental principle."}}},"has_traversal":true,"register":"oip_protocol","status":"published","revisions":2,"contributions":[],"provenance":[{"ts":"2026-07-17T02:36:50.025Z","model":"owner","action":"voxel_divide","prompt":"","input":"oip-what-is-cli","response":"63 DIVs from body (verbatim, roundtrip-checked)","tokens_in":0,"tokens_out":0,"cost":0,"prev":"genesis","hash":"b024fb9664c072a3120a6abf346156a2dad5a22a93800c436713b58dc527c19b"}],"energy":{"passes":1,"tokens_in":0,"tokens_out":0,"tokens_total":0,"cost_usd":0,"models":{"owner":1},"head":"b024fb9664c072a3120a6abf346156a2dad5a22a93800c436713b58dc527c19b"},"posted_at":"2026-07-04T18:31:27.314Z","created_at":"2026-07-04T18:31:27.314Z","updated_at":"2026-07-17T02:36:50.025Z","machine":{"shape":"article.machine/v1","slug":"oip-what-is-cli","kind":"corpus","read":{"human":"https://miscsubjects.com/a/oip-what-is-cli","json":"https://miscsubjects.com/api/articles/oip-what-is-cli","bundle":"https://miscsubjects.com/api/articles/oip-what-is-cli/bundle?format=markdown"},"traversal":{"prev":{"slug":"oip-what-is-webhook","human":"https://miscsubjects.com/a/oip-what-is-webhook","json":"https://miscsubjects.com/api/articles/oip-what-is-webhook"},"next":{"slug":"oip-what-is-oauth","human":"https://miscsubjects.com/a/oip-what-is-oauth","json":"https://miscsubjects.com/api/articles/oip-what-is-oauth"},"hub":{"slug":"philosophy","human":"https://miscsubjects.com/a/philosophy","json":"https://miscsubjects.com/api/articles/philosophy"},"series":"oip-what-is","position":15,"of":19},"ledger":{"claims":3,"sources":1,"contributions":0,"revisions":2,"objections_url":"https://miscsubjects.com/api/articles/oip-what-is-cli/objections","thread_state_url":"https://miscsubjects.com/api/protocol/thread-state?target=oip-what-is-cli","proof_rule":"An action is proven by its ledger receipt, never by a 200 or a description."},"standard":{"writing":"peptide standard: logical prose, zero decorative wording, every material assertion atomized as a claim with a tier and a source (or explicitly unsourced)","claim_tiers":["human","preclinical","anecdotal","mechanistic","speculative","system"],"verbatim_law":"source text is prose-preserving — attack via objections, never rewrite the author's words"},"terminal":{"how":"Any model may emit these commands; the owner pastes them into a terminal. $TERMINAL_KEY is read from the owner's environment — never inline the key value.","claim_append":"curl -s -X POST https://miscsubjects.com/api/protocol/claim -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"oip-what-is-cli\",\"text\":\"<one atomized claim>\",\"tier\":\"<human|preclinical|anecdotal|mechanistic|speculative|system>\",\"source_ids\":[],\"who_claims\":\"<model>\",\"rationale\":\"<why material>\"}'","source_append":"curl -s -X POST https://miscsubjects.com/api/protocol/sources -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"oip-what-is-cli\",\"sources\":[{\"type\":\"review\",\"url\":\"<url>\",\"title\":\"<title>\",\"quote\":\"<verbatim quote>\",\"summary\":\"<one line>\"}]}'","objection":"curl -s -X POST https://miscsubjects.com/api/articles/oip-what-is-cli/objections -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"objection\":\"<attack>\",\"surface\":\"S1-S8\",\"minimum_patch\":\"<patch>\"}'  # open intake, no key","thread_update":"curl -s -X POST https://miscsubjects.com/api/protocol/thread-update -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"target\":\"oip-what-is-cli\",\"raw_text\":\"<material delta>\"}'  # open intake, no key","read_back":"curl -s https://miscsubjects.com/api/articles/oip-what-is-cli | python3 -c 'import json,sys; d=json.load(sys.stdin); print(json.dumps(d[\"claims\"][-3:], indent=1))'"}},"representations":{"article":"/a/oip-what-is-cli","json":"/api/articles/oip-what-is-cli","markdown":"/api/articles/oip-what-is-cli/bundle?format=markdown","skill":"/api/articles/oip-what-is-cli/skill","topology":"/api/articles/oip-what-is-cli/topology","versions":"/api/articles/oip-what-is-cli/revisions","invocations":"/api/articles/oip-what-is-cli/invocations"},"editorial_review":null,"editorial_audit":{"slug":"oip-what-is-cli","ok":false,"issues":[{"code":"heading_filing_label","message":"section heading “Why It Matters” is a filing label that gives a cold reader no claim","replacement":"Replace “Why It Matters” with the concrete claim, event, or object introduced in that section."},{"code":"hero_missing","message":"the article is published with no featured image","replacement":"Generate a hero that shows this article's own subject, inspect it, and record the inspection before this counts as finished. An article with no image is not finished."}]},"body_hash":"e725b079b32a02f0ed3c8f567c11da3d9835f138b94d8bcb1b903da71ade3509"}}}