@brainervirus/workit-cursor 8.9.1 → 8.11.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@brainervirus/workit-cursor",
-  "version": "8.9.1",
+  "version": "8.11.0",
   "private": false,
   "description": "Workit Cursor plugin — shared MCP transport, native hooks, and sixteen method skills",
   "keywords": [
@@ -46,8 +46,8 @@
     "build": "bun scripts/build.ts"
   },
   "dependencies": {
-    "@brainervirus/workit-core": "^8.9.1",
-    "@brainervirus/workit-mcp": "^8.9.1"
+    "@brainervirus/workit-core": "^8.11.0",
+    "@brainervirus/workit-mcp": "^8.11.0"
   },
   "engines": {
     "node": ">=24"

package/rules/workit-contract.mdc

@@ -32,4 +32,7 @@ each runs in its own git worktree with a fixed brief, and its file scope is
 checked at fan-in with `git diff --name-only <base>...<branch>`, not enforced
 while it works. Verifiers and reviewers stay read-only and record
 `workit ledger verdict` under a session the lead assigns
-(`WORKIT_SESSION_ID=<lead>-v<n>` in the brief), never the author's.
+(`WORKIT_SESSION_ID=<lead>:verifier-<random hex>` in the brief, a fresh
+suffix per verifier: Cursor's shell carries no session id, so this declared
+child id is the verifier's session), never the
+author's.

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

@@ -25,7 +25,7 @@ REPORT: branch, head SHA, files changed, each VERIFY command with its exit code,
   each ACCEPTANCE line met / not met, rulings you made (`workit ledger ruling`),
   anything out of scope as a follow-up, not a diff.
 STANDING: <the standing orders, verbatim: `workit ledger standing add` records each one>
-  export WORKIT_SESSION_ID=<lead>-w<n>   (set by the lead; a verifier brief gets <lead>-v<n>)
+  export WORKIT_SESSION_ID=<lead>-w<n>   (set by the lead for a worker's commits; a verifier brief sets none: the host derives it)
 ```
 
 ## Worked example

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

@@ -72,12 +72,22 @@ Which session id a verdict carries, per host:
 
 - Claude Code: subagents inherit your `WORKIT_SESSION_ID`, so the
   SubagentStart hook names each `verifier` and `reviewer` its own session
-  (`<lead>:<agent id>`), passed as `--session`; that one wins over any
-  `<lead>-v<n>` in a brief. An `implementer` uses the session its brief
-  exports for its workit commands.
-- Other hosts: the session the brief sets wins: `export
-  WORKIT_SESSION_ID=<lead>-w-<slice>` from `workit fanout brief` for a
-  worker, `<lead>-v<n>` (or `--as verifier`) for a verifier you start.
+  (`<lead>:<agent id>`), passed exactly as `--session`: the hook records the
+  ids it issues, and only those are accepted. An `implementer` uses the
+  session its brief exports for its workit commands.
+- Codex: the `workit-verifier` and `workit-reviewer` agents get the same
+  issued `--session` from SubagentStart; any other verifier passes
+  `--as verifier`.
+- OpenCode: a child session's shell already has
+  `WORKIT_SESSION_ID=<lead>:<child>`; Pi: a supervised worker's shell has
+  `<lead>:<worker session>`. Set nothing for a verifier there.
+- Cursor (no session id in the shell): the brief sets the verifier's
+  `WORKIT_SESSION_ID=<lead>:verifier-<random hex>`, a fresh suffix per
+  verifier. Cursor cannot check it: it is declared, not derived.
+- A worker's commits use `export WORKIT_SESSION_ID=<lead>-w-<slice>` from
+  `workit fanout brief`. A verdict under an id you made up (`<lead>-v1`,
+  `<lead>:v1`) is refused as `forged_session` on Claude Code, Codex,
+  OpenCode and Pi.
 
 A batch verifier takes several slices on one surface in one session: for
 each branch it checks out the head, runs that slice's VERIFY, and records its

package/skills/workit-implement/SKILL.md

@@ -33,8 +33,9 @@ description: Build a requested change in small verified steps - follow local pat
    `workit ledger verdict tests-verified --self --how "<what you ran>"`; it
    reads self-reviewed, never verified. High risk, a workspace with
    `verification: independent` (`workit grant show`) or a verified merge needs
-   a fresh verifier with its own session (`WORKIT_SESSION_ID=<yours>-v1`;
-   Claude Code: the `verifier` agent). Before saying done, reconcile
+   a fresh verifier with its own host-derived session (Claude Code and Codex:
+   the `verifier` agent; OpenCode: a child session; Pi: a supervised worker),
+   never a hand-minted id. Before saying done, reconcile
    every named deliverable against the target checkout and observe it (for a push:
    `workit verify-delivery push`).
 

package/skills/workit-review/SKILL.md

@@ -7,8 +7,10 @@ description: Independent review of a diff, branch or PR - intent fidelity and st
 
 Review the candidate, never the author's summary of it. A session that wrote a
 commit on the branch cannot record a passing verdict: if that is you, hand the
-review to a fresh agent with its own session (`WORKIT_SESSION_ID=<lead>-v<n>`;
-Claude Code: the `reviewer` or `verifier` agent).
+review to a fresh agent with its own host-derived session: Claude Code and
+Codex, the `reviewer` or `verifier` agent (`--session` from SubagentStart);
+OpenCode, a child session; Pi, a supervised worker. Never hand-mint one such
+as `<lead>-v1`: it is refused as `forged_session`.
 An author's `--self` verdict reads self-reviewed and never counts as
 independent; `type-check-only` never proves a behavior change.