@brainervirus/workit-codex 8.17.1 → 8.19.0

package/dist/workit-hook.js

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 import {
   maybeHeavy
-} from "./workit-hook-rbb0m9zp.js";
+} from "./workit-hook-8yfjygc1.js";
 
 // packages/workit-codex/hooks/launcher.ts
 var payload = "";
@@ -39,6 +39,6 @@ if (quiet)
   process.stdout.write(`${JSON.stringify({ hookSpecificOutput: { hookEventName: quiet } })}
 `);
 else {
-  const { runCodexHook } = await import("./workit-hook-5g0b5ywj.js");
+  const { runCodexHook } = await import("./workit-hook-rkwtxnyc.js");
   await runCodexHook([payload]);
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@brainervirus/workit-codex",
-  "version": "8.17.1",
+  "version": "8.19.0",
   "private": false,
   "description": "Workit Codex CLI/desktop plugin — shared MCP transport, hooks, method skills, and verifier/reviewer/implementer agents",
   "keywords": [
@@ -39,8 +39,8 @@
     "build": "bun scripts/build.ts"
   },
   "devDependencies": {
-    "@brainervirus/workit-core": "^8.17.1",
-    "@brainervirus/workit-mcp": "^8.17.1"
+    "@brainervirus/workit-core": "^8.19.0",
+    "@brainervirus/workit-mcp": "^8.19.0"
   },
   "engines": {
     "node": ">=24"

package/skills/workit-bdd/SKILL.md

@@ -22,7 +22,7 @@ description: Turn requirements into Given/When/Then scenarios, agree the test se
    then take the next scenario. Any edit makes the observation stale; re-run
    before you claim it. A recorded "tests pass" is a note, and an ad-hoc
    `workit check -- <cmd>` never satisfies the gate: only the configured
-   `test` check does. No `test` detected? Create `workit.checks.json`, copying
+   `test` check does. No `test` detected? Create `.workit/checks.json`, copying
    in every check the repo already runs: once it exists it replaces the
    detected defaults.
 5. **Mock only at system boundaries:** network, clock, randomness, other

package/skills/workit-fanout/SKILL.md

@@ -37,8 +37,8 @@ units of ~100+ lines each. Coupled work stays with one owner. Workit never spawn
 6. **Retry once, then escalate.** A stuck or failed slice gets one retry with
    a fresh brief (`workit fanout brief <slice> --mode resume`, same branch);
    if that fails too, re-slice it, take it over, or report the gap. Never
-   chain resumes. A hard slice may race instead: N attempts, keep the best
-   verdict (`references/orchestration.md`).
+   chain resumes. A fix round and recheck that both fail: a decider, not a
+   third round; product choices go to the user (`references/orchestration.md`).
 7. **Verify by the workspace `verification` setting** (`workit grant show`).
    A report is a pointer, never evidence. `self`: a verifier that wrote none
    of the slices, or you if you wrote none. `independent` or high risk: a

package/skills/workit-fanout/references/orchestration.md

@@ -43,6 +43,27 @@ rulings). If the retry fails too, escalate instead of a third worker:
 re-slice it smaller (`workit fanout plan` again), take it over yourself, or
 report the gap to the user.
 
+## Stuck calls: the decider
+
+A failed review gets one fix round and one recheck (the changed hunks only).
+If the recheck fails, or a worker and a reviewer disagree, spawn a decider
+instead of a third round. A decider is a fresh read-only agent, not the author
+or the reviewer. It returns three things: the options, a pick by
+reversibility (the option cheapest to undo wins a tie), and the exact change
+list. The fixer applies that list once, then one focused recheck follows.
+
+- Hard call (shared contract, security, migration): two deciders on different
+  models (Claude Code: a different `model` on the Agent call; OpenCode: a
+  child session on another configured agent; Codex, Cursor and Pi: one
+  decider, since the host picks no model). If they disagree, you take the
+  more reversible option.
+- Record it: `workit ledger decision "<pick>" --by decider --why "<why it is
+  the more reversible>" --view "<decider A: view>" --view "<decider B: view>"`.
+  The row is listed as a decider call; it is never the user's answer to a
+  product choice and never a verdict.
+- A product choice, or authority nobody here has, is not a decider's call:
+  ask the user with your recommendation.
+
 ## Race a hard slice
 
 When a hard slice has an uncertain approach and a cheap VERIFY, run 2-3

package/skills/workit-retro/SKILL.md

@@ -32,7 +32,7 @@ proposes and stops. Nothing changes until the user approves.
    more cited occurrences**; a one-off is not a learning.
 4. **Name the strongest enforcer that works**, strongest first: architecture
    or types (the mistake cannot be written) > lint rule > configured check
-   (`workit.checks.json`, `workit check <name>`) or CI job > test >
+   (`.workit/checks.json`, `workit check <name>`) or CI job > test >
    `CODING_STANDARDS.md` (judgment the reviewer reads) > AGENTS.md pointer
    (navigation only). A mechanical rule gets a check, not prose: a check can
    fail, a sentence cannot. From types to test, the proof is that the new
@@ -60,7 +60,7 @@ Bad: "Agents seem lost in the build. Added 'read the build docs carefully' to
 AGENTS.md." One vague occurrence, no citation, a no-op line, auto-applied.
 
 Good: "Navigation, 3 occurrences (rulings 12, 19; PR #88 thread): agents sought
-check names in package.json, missing `workit.checks.json`. Enforcer: AGENTS.md
+check names in package.json, missing `.workit/checks.json`. Enforcer: AGENTS.md
 pointer, +74 bytes, minus the stale Commands paragraph (-210). Unstable check,
 2 occurrences (ledger rows 31, 44: `e2e` red then green on one SHA): a debug
 slice to fix the check. Approve?"

package/skills/workit-review/SKILL.md

@@ -36,7 +36,10 @@ independent; `type-check-only` never proves a behavior change.
 7. Record the verdict:
    `workit ledger verdict verified|failed|blocked --kind review --branch <b> --how "<what you ran and read>"`
    under your own session (the one the lead or the hook gave you).
-8. **Harness note** (optional): friction caused by the repo or harness, not
+8. **Bound the loop.** A failed verdict gets one fix round and one recheck of
+   the changed hunks. Still failing, or stuck: no third round; the lead spawns
+   a decider (read the `workit-fanout` skill's SKILL.md and follow it). A product choice goes to the user.
+9. **Harness note** (optional): friction caused by the repo or harness, not
    the change (a flaky fixture, a missing check, a misleading doc or skill
    line), goes on its own `Harness note:` line in the report and any PR
    comment, never as a finding or in the verdict, so a later retro finds it.

package/skills/workit-ship/SKILL.md

@@ -30,7 +30,7 @@ once the verdict is accepted. `merged`: step 7. `null` (closed, not merged):
 stop and report. Stop early only for a new consequential choice, a host
 denial, a review comment that needs a product decision, a required update
 that repeats because the base keeps moving, or after 3 failed fix attempts on
-the same check.
+the same check. Fix round and recheck both failed: a decider (read the `workit-fanout` skill's SKILL.md and follow it).
 
 1. **Open.** `workit git push`, then `workit pr create --title "<title>"
    --body-file <f|->` plus `--issue <#n|ID>` per issue (`--refs`: no close; idempotent;

package/skills/workit-verify-app/SKILL.md

@@ -35,7 +35,7 @@ way a user would.
    never run is a guess; do not hand it off.
 4. **Make the driver a named check** when it is cheap and deterministic. A
    named check is one command without shell syntax (put pipes and setup in a
-   script). Add `"verify": "<driver>"` to `checks` in `workit.checks.json`; if
+   script). Add `"verify": "<driver>"` to `checks` in `.workit/checks.json`; if
    the file does not exist yet, first copy in every check the repo already runs
    (test, lint, typecheck), because the file replaces the detected defaults.
    `workit check verify` then records it, and it joins the verification gate