jetthoughts · pftg · Aug 21, 2026 · Aug 21, 2026 · Aug 21, 2026
diff --git a/.claude/commands/deliver.md b/.claude/commands/deliver.md
diff --git a/.claude/settings.json b/.claude/settings.json
@@ -36,6 +36,17 @@
         ]
       }
     ],
+    "SubagentStop": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node .claude/helpers/hook-handler.cjs post-task || true",
+            "timeout": 10
+          }
+        ]
+      }
+    ],
     "SessionEnd": [
       {
         "hooks": [

diff --git a/.okf/log.md b/.okf/log.md
@@ -2547,3 +2547,18 @@ jt-gotcha-cli-semantic-search-broken: CLI semantic empty without ruvector;
 global HNSW misses CLI-written vectors until server restart (scoped search
 finds them); sql.js whole-image flushes resurrect external SQL deletes -
 mutate only via MCP/CLI, never raw SQL while the server runs.
+
+## 2026-08-21 - ADR-0005 extraction shipped: jt-delivery plugin v0.1.0
+
+jetthoughts/claude-plugins created (public - the contract was already public
+in this repo); plugin jt-delivery v0.1.0: contract skill (genericized par.1-9),
+/deliver, async-first skill, five core author/verifier agents. Pre-publish
+review: 1 blocking + 5 minor, all fixed - notably a verifier-briefing
+regression (the skill had reverted to blind-briefing; restored
+reasoning-handover + one-independent-measurement per the verifiers-need-the-
+reasoning correction). Marketplace format gotchas: owner object required;
+plugin source must be a plain string path, not the {source,path} object some
+cached marketplaces use. This repo's delivery prompt became a 241-line repo
+binding (was 662): SHIP gate matrix, canon/OKF/memory contract additions,
+reviewer routing, Appendices A-C; generic par.1-9 deleted per the ADR's
+net-deletion rule; repo /deliver command deleted (plugin provides it).
diff --git a/.okf/workflows/autonomous-loops.md b/.okf/workflows/autonomous-loops.md
@@ -74,11 +74,14 @@ gate rules that would otherwise decay. The 1a.4 prompt carried "never cite
 `[snap_diff] N screenshots compared` count", and "`--strict` EXITS 1 by design",
 and none of those was violated across the whole run.
 
-# The delivery prompt that wraps this
-
-`docs/workflows/autonomous-delivery-prompt.md` is the operating prompt for
-running a goal unattended: DISCOVER -> DECIDE -> BUILD -> VERIFY -> 4-EYES ->
-SHIP -> LEARN, WIP=1, with the evidence ladder and the review-panel rules.
+# The delivery contract that wraps this
+
+The `jt-delivery:contract` skill (plugin `jt-delivery@jetthoughts`, per
+ADR-0005) is the operating contract for running a goal unattended:
+DISCOVER -> DECIDE -> BUILD -> VERIFY -> 4-EYES -> SHIP -> LEARN, WIP=1,
+with the evidence ladder and the review-panel rules. The repo-specific
+bindings (gate matrix, canon, reviewer routing, Appendices) live in
+`docs/workflows/autonomous-delivery-prompt.md`.
 
 It is the complement to this concept rather than a competitor. This file says
 what a self-iterating LOOP can and cannot do; that file says what a delivery

diff --git a/AGENTS.md b/AGENTS.md
@@ -5,7 +5,7 @@ Session start: always read `@docs/workflows/BASE_HANDBOOK.md` and `@docs/workflo
 
 **Async-first communication (SOP for ALL agents):** written, discoverable artifacts are the default for every decision, finding, status change, and handoff — sync interaction is the exception and its outcome gets written back same-day. Full rules + canonical surfaces table: `.agents/skills/async-first-communication/SKILL.md`. A task is not done until its state is readable asynchronously.
 
-**Four eyes on every stage, author != verifier (SOP for ALL agents):** the point is agents collaborating to find the TRUTH — a single agent cannot find its own blind spot, because it checks the thing it MEANT to build. Every change is **written by one sub-agent and verified by a different one**; the author never produces the evidence for its own claim. The review lands before the artifact leaves the workshop: a plan is peer-reviewed BEFORE the user is asked, a diff BEFORE commit, a finding is reproduced before it is reported, a measurement re-derived before it is quoted. Brief reviewers with the goal and the artifact, never your conclusions; ask for measurements, not verdicts. Routing: internal sub-agents for every per-stage review, `/codex:review` ONCE at the final verify before merge for USER-FACING changes (it is slow — never in the inner loop); docs-only and instruction-layer changes ship on internal review + CI and apply its findings as a follow-up. No reviewer tooling in this runtime? Fall back agent → external → peer session → human, and mark the change UNREVIEWED if none is reachable. Full protocol: `docs/workflows/autonomous-delivery-prompt.md`.
+**Four eyes on every stage, author != verifier (SOP for ALL agents):** the point is agents collaborating to find the TRUTH — a single agent cannot find its own blind spot, because it checks the thing it MEANT to build. Every change is **written by one sub-agent and verified by a different one**; the author never produces the evidence for its own claim. The review lands before the artifact leaves the workshop: a plan is peer-reviewed BEFORE the user is asked, a diff BEFORE commit, a finding is reproduced before it is reported, a measurement re-derived before it is quoted. Brief reviewers with the goal and the artifact, never your conclusions; ask for measurements, not verdicts. Routing: internal sub-agents for every per-stage review, `/codex:review` ONCE at the final verify before merge for USER-FACING changes (it is slow — never in the inner loop); docs-only and instruction-layer changes ship on internal review + CI and apply its findings as a follow-up. No reviewer tooling in this runtime? Fall back agent → external → peer session → human, and mark the change UNREVIEWED if none is reachable. Full protocol: the `jt-delivery:contract` skill (plugin `jt-delivery@jetthoughts`); repo bindings: `docs/workflows/autonomous-delivery-prompt.md`.
 
 **Session memory (ruflo-first, SOP for ALL agents):** search ruflo memory (`mcp__ruflo__memory_search`, MCP path) before non-obvious decisions; store decisions/corrections via `mcp__ruflo__memory_store` as they land. Details + prefix conventions: `CLAUDE.md` §Memory.
 

diff --git a/CLAUDE.md b/CLAUDE.md
@@ -78,9 +78,9 @@ Operational knowledge lives in `.okf/` (`build/`, `content/`, `design/`, `workfl
 
 ## 🚨 Behavioral Constraints
 
-- **Feature/idea intake**: `/deliver <idea>` (or §1a of `docs/workflows/autonomous-delivery-prompt.md`) — triage → GOAL → author≠verifier orchestration under the contract.
+- **Feature/idea intake**: `/deliver <idea>` (from the `jt-delivery` plugin) — triage → GOAL → author≠verifier orchestration per the `jt-delivery:contract` skill §1a; repo-specific bindings (gates, canon, reviewer routing): `docs/workflows/autonomous-delivery-prompt.md`.
 - **Manager triage (Paul 2026-08-01)**: Paul adds requests mid-flight; triage each against the active plan — now / sequenced / backlog / groom-first — and report the verdict in one line so he can override. Deferring is a decision; interrupting a gated pipeline for a non-critical request is the failure. **Autonomy grant**: handle sprints end-to-end; for big/critical calls run a 2-4 agent voting panel and make the call (split + irreversible → hold for Paul). Record every autonomous call with its evidence. Paul's explicit words override any panel.
-- **Agent 4-eyes on EVERY stage, author ≠ verifier (Paul 2026-08-20, widened 2026-08-21)**: every change is written by one agent and verified by a different one; review lands BEFORE the artifact leaves the workshop (plan before Paul sees it, diff before commit, finding before reported, measurement before quoted). Brief reviewers with goal + artifact, never conclusions; ask for measurements, not verdicts. Internal sub-agents per stage; `/codex:review` once at the merge gate for user-facing changes. Full protocol: `docs/workflows/autonomous-delivery-prompt.md` §5. (Evidence: 2026-08-20/21 — reviewers caught a CSS-breaking defect, a fabricated quote, and 11 findings on the delivery prompt itself, all after author self-review.)
+- **Agent 4-eyes on EVERY stage, author ≠ verifier (Paul 2026-08-20, widened 2026-08-21)**: every change is written by one agent and verified by a different one; review lands BEFORE the artifact leaves the workshop (plan before Paul sees it, diff before commit, finding before reported, measurement before quoted). Brief reviewers with goal + artifact, never conclusions; ask for measurements, not verdicts. Internal sub-agents per stage; `/codex:review` once at the merge gate for user-facing changes. Full protocol: `jt-delivery:contract` skill §5; repo routing: `docs/workflows/autonomous-delivery-prompt.md`. (Evidence: 2026-08-20/21 — reviewers caught a CSS-breaking defect, a fabricated quote, and 11 findings on the delivery prompt itself, all after author self-review.)
 - **Async-first (MANDATORY)**: written, discoverable artifacts for every decision, finding, and handoff; sync is the exception, written back same-day. A task is not done until a cold session can read its state with zero questions. Canonical surfaces: `.agents/skills/async-first-communication/SKILL.md`; same SOP in `AGENTS.md`.
 - **Company facts have a canon**: check `.okf/content/claims-canon.md` before publishing any number (founding 2008-09-01; tenure from `site.Params.foundingYear`; "4.8/5 on Clutch" linked, NO review count; founder 22+ vs company 18+). A number with no in-repo source is a defect. Correcting one means sweeping the instruction layer too — `PRODUCT.md`, `docs/business/`, outreach kits have re-introduced bad canon before (4 of 8 published figures were wrong on 2026-08-14).
 - **Text ratchets read RENDERED output, not source**: `marketing_copy_test` globs source and missed three rendered-only defects on 2026-08-14 (unglobbed partial, line-wrapped banned phrase, composed nested `<main>`). Queued: `docs/20-29-testing-qa/20.10` §3b P0-4.

diff --git a/docs/adr/0005-reusable-ai-instruction-layer.md b/docs/adr/0005-reusable-ai-instruction-layer.md
@@ -2,7 +2,7 @@
 
 **ADR-0005**
 **Date:** 2026-08-21
-**Status:** Accepted (2026-08-21 — direction set by Paul's reuse request; mechanism chosen per alternatives analysis; reversible until the extraction sprint ships)
+**Status:** Accepted (2026-08-21 — direction set by Paul's reuse request; mechanism chosen per alternatives analysis; extraction shipped same day: plugin v0.1.0 + migration PR)
 
 ## Title