{ "protocol": "OIP", "version": "1.2.0", "kind": "ask", "question": "governor", "count": 5, "best": { "key": "GOVERNOR", "run_now": "https://miscsubjects.com/api/dispatch?invoke=GOVERNOR&body=%3Cyour%20request%20in%20plain%20words%3E&share=", "do": "Open run_now to do it. Substitute your own text/args where the example has them." }, "matches": [ { "key": "GOVERNOR", "what": null, "when_to_use": null, "category": "governance", "runner": "model", "example": "[GOVERNOR][/GOVERNOR]", "example_args": "", "example_source": "derived", "run_now": "https://miscsubjects.com/api/dispatch?invoke=GOVERNOR&body=%3Cyour%20request%20in%20plain%20words%3E&share=", "invoke": { "post": "https://miscsubjects.com/api/dispatch", "body": { "key": "GOVERNOR", "body": "" }, "router": "[GOVERNOR]args[/GOVERNOR]" }, "self": "https://miscsubjects.com/api/dispatch?key=GOVERNOR" }, { "key": "GOVERNOR_RUN", "what": "Run the GOVERNOR — scan the last 48h of ledger turns into a deterministic digest (error streaks, file collisions, loop states, auth lockouts, cron noise, task flow, waste), have the GOVERNOR model write the brief, email it to the custodian, text him the verdict, ledger everything as GOVERNOR_BRIEF.", "when_to_use": "the custodian asks \"whats going on with the build\", \"governor report\", \"run governor\", \"build brief\", \"what keeps breaking\" — or any model wants the standing manager's view before making structural changes. Runs automatically every 12h / 2000 events / 150 errors; this row is the manual fire.", "category": "governance", "runner": "fn", "example": "[GOVERNOR_RUN][/GOVERNOR_RUN] or GET /api/dispatch?invoke=GOVERNOR_RUN&body=dry", "example_args": "", "example_source": "curated", "run_now": "https://miscsubjects.com/api/dispatch?invoke=GOVERNOR_RUN&share=", "invoke": { "post": "https://miscsubjects.com/api/dispatch", "body": { "key": "GOVERNOR_RUN", "body": "" }, "router": "[GOVERNOR_RUN]args[/GOVERNOR_RUN]" }, "self": "https://miscsubjects.com/api/dispatch?key=GOVERNOR_RUN" }, { "key": "GOVERNOR_ASK", "what": "Ask the GOVERNOR (build manager) a question. It answers from the live 24h digest + recurrence memory + charter — counts in parentheses, sized for iMessage.", "when_to_use": "the custodian texts \"governor \" or \"ask the governor ...\", or any model wants the manager's evidence-grounded read on build health, conflicts, or what keeps recurring.", "category": "governance", "runner": "fn", "example": "[GOVERNOR_ASK]why is the task backlog so big[/GOVERNOR_ASK]", "example_args": "why is the task backlog so big", "example_source": "curated", "run_now": "https://miscsubjects.com/api/dispatch?invoke=GOVERNOR_ASK&body=why%20is%20the%20task%20backlog%20so%20big&share=", "invoke": { "post": "https://miscsubjects.com/api/dispatch", "body": { "key": "GOVERNOR_ASK", "body": "why is the task backlog so big" }, "router": "[GOVERNOR_ASK]args[/GOVERNOR_ASK]" }, "self": "https://miscsubjects.com/api/dispatch?key=GOVERNOR_ASK" }, { "key": "ROUTER", "what": null, "when_to_use": null, "category": "agent", "runner": "model", "example": "[ROUTER][/ROUTER]", "example_args": "", "example_source": "derived", "run_now": "https://miscsubjects.com/api/dispatch?invoke=ROUTER&body=%3Cyour%20request%20in%20plain%20words%3E&share=", "invoke": { "post": "https://miscsubjects.com/api/dispatch", "body": { "key": "ROUTER", "body": "" }, "router": "[ROUTER]args[/ROUTER]" }, "self": "https://miscsubjects.com/api/dispatch?key=ROUTER" }, { "key": "PROSECUTOR_RUN", "what": "One machine turn of the operator loop, end to end: fetch the drop + current accepted thread-state, ask a model for ONE materially new point (inheriting all accepted state, never repeating it), and post the result to the thread bus as a proposed update. Replies NOTHING NEW when the state already covers everything it sees.", "when_to_use": "the custodian says \"prosecute the protocol\", \"run the loop\", \"have a machine critique it\" — or the governor wants fresh adversarial load without any human transport.", "category": "governance", "runner": "fn", "example": "[PROSECUTOR_RUN]ASK_KIMI[/PROSECUTOR_RUN]", "example_args": "ASK_KIMI", "example_source": "curated", "run_now": "https://miscsubjects.com/api/dispatch?invoke=PROSECUTOR_RUN&body=ASK_KIMI&share=", "invoke": { "post": "https://miscsubjects.com/api/dispatch", "body": { "key": "PROSECUTOR_RUN", "body": "ASK_KIMI" }, "router": "[PROSECUTOR_RUN]args[/PROSECUTOR_RUN]" }, "self": "https://miscsubjects.com/api/dispatch?key=PROSECUTOR_RUN" } ], "compose": "Multiple targets (e.g. text 3 people)? Repeat the call once PER target — one invoke each, one receipt each. Don't cram a list into one call unless the row's args say it takes one. Multi-step (make an image THEN text it)? Do the steps in order, feeding each result into the next.", "json_and_post_free": "Needs a JSON body or looks 'POST-only'? You don't need POST. url-encode the JSON into &body= (?invoke=KEY&body=), or use the row's pipe args (a|b|c). Every write is a GET row — edit a prompt: DIR_PATCH body=KEY|{\"content\":\"...\"}; write/revise an article: PROTOCOL_WRITE body=; ingest: ARTICLE_INGEST body=slug|text.", "reply_contract": "OUTPUT RULE — after you invoke ANYTHING, your reply to the user IS the proof, never \"sent it\": for each action paste one line — \"✓ — receipt: \" (or \"✗ FAILED: \" when the response has ran:false / can_act:false / ok:false). N actions → N lines, N receipts. Never claim an action you have no receipt for; never fabricate a URL, count, or outcome.", "note": "Best match first. Each row's run_now is a URL that fires it with real example args — open it, swapping in your own values. No guessing: the example IS the shape. Then reply per reply_contract.", "registry": "https://miscsubjects.com/api/dispatch?registry=1" }