Clarify scheduler completion publish flow

package.json

@@ -34,7 +34,8 @@
     "lock:lock": "node bin/torch-lock.mjs lock",
     "dashboard:serve": "node bin/torch-lock.mjs dashboard",
     "build": "node build.mjs",
-    "lint": "eslint ."
+    "lint": "eslint .",
+    "lock:complete": "node bin/torch-lock.mjs complete"
   },
   "dependencies": {
     "nostr-tools": "2.19.4",

src/prompts/META_PROMPTS.md

@@ -50,7 +50,18 @@ MUST 3: Run these commands in this order:
    Exit 0 = lock acquired, proceed. Exit 3 = race lost, go back to step 3.
 6) Execute selected prompt from src/prompts/daily/
 7) Run repository checks (for example: npm run lint)
-8) Create `_completed.md` or `_failed.md`, commit, push
+8) Publish completion before writing `_completed.md`:
+   AGENT_PLATFORM=<platform> npm run lock:complete -- --agent <agent-name> --cadence daily
+   (Equivalent command allowed: torch-lock complete --agent <agent-name> --cadence daily)
+   - Exit 0: continue.
+   - Exit non-zero: fail the run, write `_failed.md` with a clear completion-publish failure reason and retry guidance, then stop.
+9) Only after step 8 succeeds, write final task log (`_completed.md` for success, `_failed.md` for failure), commit, push
+
+   Worked example (required order):
+   - `AGENT_PLATFORM=codex npm run lock:lock -- --agent content-audit-agent --cadence daily`
+   - execute selected prompt work
+   - `AGENT_PLATFORM=codex npm run lock:complete -- --agent content-audit-agent --cadence daily` (complete, permanent)
+   - write `task-logs/daily/<timestamp>__content-audit-agent__completed.md`
 
 MUST 4: If all daily agents are excluded, stop and write `_failed.md` with this exact reason: `All roster tasks currently claimed by other agents`.
 ```
@@ -101,7 +112,18 @@ MUST 3: Run these commands in this order:
    Exit 0 = lock acquired, proceed. Exit 3 = race lost, go back to step 3.
 6) Execute selected prompt from src/prompts/weekly/
 7) Run repository checks (for example: npm run lint)
-8) Create `_completed.md` or `_failed.md`, commit, push
+8) Publish completion before writing `_completed.md`:
+   AGENT_PLATFORM=<platform> npm run lock:complete -- --agent <agent-name> --cadence weekly
+   (Equivalent command allowed: torch-lock complete --agent <agent-name> --cadence weekly)
+   - Exit 0: continue.
+   - Exit non-zero: fail the run, write `_failed.md` with a clear completion-publish failure reason and retry guidance, then stop.
+9) Only after step 8 succeeds, write final task log (`_completed.md` for success, `_failed.md` for failure), commit, push
+
+   Worked example (required order):
+   - `AGENT_PLATFORM=codex npm run lock:lock -- --agent bug-reproducer-agent --cadence weekly`
+   - execute selected prompt work
+   - `AGENT_PLATFORM=codex npm run lock:complete -- --agent bug-reproducer-agent --cadence weekly` (complete, permanent)
+   - write `task-logs/weekly/<timestamp>__bug-reproducer-agent__completed.md`
 
 MUST 4: If all weekly agents are excluded, stop and write `_failed.md` with this exact reason: `All roster tasks currently claimed by other agents`.
 ```

src/prompts/scheduler-flow.md

@@ -88,4 +88,30 @@ Use this document for all scheduler runs.
 
 8. Execute `<prompt_dir>/<prompt-file>` end-to-end.
 
-9. Create exactly one final status file (`_completed.md` or `_failed.md`), run repo checks, commit, and push.
+9. Run repository checks (for example: `npm run lint`).
+
+10. Publish completion before writing final success log:
+
+    ```bash
+    AGENT_PLATFORM=<platform> \
+    npm run lock:complete -- --agent <agent-name> --cadence <cadence>
+    ```
+
+    (Equivalent invocation is allowed: `torch-lock complete --agent <agent-name> --cadence <cadence>`.)
+
+    - Exit `0`: completion published successfully; continue to step 11.
+    - Exit non-zero: **fail the run**, write `_failed.md` with a clear reason that completion publish failed and retry guidance (for example: `Retry npm run lock:complete -- --agent <agent-name> --cadence <cadence> after verifying relay connectivity`), then stop.
+
+11. Create final task log only after step 10 succeeds:
+
+    - `_completed.md` MUST be created only after completion publish succeeds.
+    - `_failed.md` is required when step 10 fails, and should include the failure reason and next retry action.
+
+12. Commit and push.
+
+Worked post-task example (MUST order):
+
+1. `AGENT_PLATFORM=codex npm run lock:lock -- --agent content-audit-agent --cadence daily`
+2. Execute `src/prompts/daily/content-audit-agent.md`
+3. `AGENT_PLATFORM=codex npm run lock:complete -- --agent content-audit-agent --cadence daily` (complete, permanent)
+4. Write `task-logs/daily/2026-02-14T10-00-00Z__content-audit-agent__completed.md`