@brainervirus/workit-cursor 8.15.1 → 8.17.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@brainervirus/workit-cursor",
-  "version": "8.15.1",
+  "version": "8.17.0",
   "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"
   },
   "devDependencies": {
-    "@brainervirus/workit-core": "^8.15.1",
-    "@brainervirus/workit-mcp": "^8.15.1"
+    "@brainervirus/workit-core": "^8.17.0",
+    "@brainervirus/workit-mcp": "^8.17.0"
   },
   "engines": {
     "node": ">=24"

package/skills/workit-fanout/SKILL.md

@@ -5,13 +5,13 @@ description: Run independent slices in parallel - one worker per isolated worktr
 
 # Fan out parallel workers
 
-Fan out only independent slices: disjoint files, no shared mutable state, each
-verifiable alone. Code-coupled work stays with one owner, who fans out after
-the blocking part lands. A worker whose whole job is re-running one command is
-ceremony; do it yourself. Workit never spawns agents; you do.
+Inline-first (workspace `delegation`): fan out only past a threshold, named as
+each slice's `reason` (explore, parallel, backstop, high-risk-verify): an
+explorer past ~3 tool calls or 10k tokens; parallel writers only for 2+ disjoint
+units of ~100+ lines each. Coupled work stays with one owner. Workit never spawns.
 
 1. **Plan the slices** (read the `workit-shape` skill's SKILL.md and follow it) in a plan file (`references/brief.md`):
-   per slice an id, branch, TIER, SCOPE globs, `owns` for shared files,
+   per slice an id, branch, REASON, TIER, SCOPE globs, `owns` for shared files,
    `dependsOn` only for a real dependency, and the brief fields. `workit fanout
    plan <plan.json>` refuses an empty or placeholder brief field (exit 2) and
    two slices that may write one file (exit 3) with a fix; apply it and re-run:
@@ -21,8 +21,8 @@ ceremony; do it yourself. Workit never spawns agents; you do.
 2. **Record standing orders** (`workit ledger standing add "<order>"`): every
    user directive all workers share. Directives decay across resumes.
 3. **Brief each worker verbatim** with `workit fanout brief <slice>`: plan
-   fields, standing orders, SCRATCH, session id, fan-in rule. Never hand-edit
-   it; change the plan or the standing orders and render again.
+   fields, standing orders, SCRATCH, session id, fan-in and heavy-lease rules.
+   Never hand-edit it; change the plan or the standing orders and render again.
 4. **Spawn in a rolling window**, in the background, each in its own worktree:
    keep 4-6 in flight and refill from `spawnable` in `workit fanout status` as
    each one finishes. Model: the brief's `model:` line, else TIER

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

@@ -59,7 +59,8 @@ defaults to the trunk, or to the branch of a single `dependsOn` slice (a
 stack); `worktree` defaults to `../<repo>-wt/<id>`. `owns` claims a shared
 file another slice's glob also matches. Globs that match no file yet are compared
 through a sample path. Use `/` as the separator; a backslash only escapes
-literal brackets: `"app/\\[id\\]/page.tsx"`. A `timebox` such as `45 minutes`
+literal brackets: `"app/\\[id\\]/page.tsx"`. A `reason` (`explore`, `parallel`, `backstop` or `high-risk-verify`) is rendered as the brief's `REASON:` line and is
+required unless the workspace sets `delegation` to `lead-orchestrates`. A `timebox` such as `45 minutes`
 is the slice's STUCK threshold in `workit fanout status`. `"fanIn":
 "integration"` (with an integration branch as `trunk`) is the one-PR mode in
 `orchestration.md`; the default `"prs"` lands one PR per slice.
@@ -79,6 +80,7 @@ is the slice's STUCK threshold in `workit fanout status`. `"fanIn":
       "acceptance": ["Given no auth header, When GET /v1/usage, Then the status is 401"],
       "verify": ["workit check test"],
       "forbidden": ["no edits outside SCOPE", "no rebase or force-push"],
+      "reason": "parallel",
       "context": "docs/usage/spec.md Behavior",
       "timebox": "45 minutes"
     },

package/skills/workit-implement/SKILL.md

@@ -19,7 +19,9 @@ description: Build a requested change in small verified steps - follow local pat
    Mechanical change: the existing checks are enough. No tautological tests:
    a test must fail if the behavior breaks, never restate the implementation.
 4. Run the real checks: `workit check test` (and `lint`, `typecheck` when the
-   repo has them).
+   repo has them). Heavy work runs under one machine-wide lease: an ad-hoc
+   suite is `workit check --heavy -- <cmd>`, never a hand-made flock; a busy
+   lease waits and names its holder (`workit lock status`).
 5. Prove the feature on its real surface with the project's `verify-<app>`
    skill; none yet? Write one (read the `workit-verify-app` skill's SKILL.md and follow it). Tests show branch behavior,
    not that the feature works.
@@ -41,6 +43,11 @@ description: Build a requested change in small verified steps - follow local pat
 
 Independent slices that could run in parallel: fan them out (read the `workit-fanout` skill's SKILL.md and follow it).
 
+Stay inline by default (workspace `delegation: inline-first`). Hand work off
+only past the thresholds: an explorer after about 3 tool calls or 10k tokens
+of searching, parallel writers for 2 or more disjoint units of about 100+
+lines each.
+
 ## Example
 
 Bad: "Done - added the --since flag, tests pass." (no check ran this turn; the

package/skills/workit-review/SKILL.md

@@ -24,7 +24,8 @@ independent; `type-check-only` never proves a behavior change.
    - **Standards:** repo rules first (`CODING_STANDARDS.md` when present),
      then a smell baseline (unclear name, long function, duplicated logic,
      leaky abstraction). Judgment only; lint owns nits.
-4. **Tests:** `workit test-audit --diff`. Would each new test fail if the
+4. **Tests:** run suites under the heavy-check lease (`workit check test`,
+   `workit check --heavy -- <cmd>`); `workit test-audit --diff`. Would each new test fail if the
    behavior broke? Triage the findings (read the `workit-test-audit` skill's SKILL.md and follow it).
 5. **Blast radius:** for each touched contract, caller, config or migration,
    state the one fact it is safe because of and run the proof. Anything

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

@@ -21,6 +21,8 @@ way a user would.
    `.cursor/skills/`; other hosts: the directory their docs name). If the repo
    already has a project skills directory, use it:
    - **Launch:** one command, its ready signal (log line, port, exit 0), a timeout.
+     Builds, installs and e2e suites run under the heavy-check lease
+     (`workit check --heavy -- <cmd>`); a long-running server does not.
    - **Doctor:** each precondition and its fix (deps, env vars, ports, services).
    - **Drive:** how to exercise it: CLI invocations, `curl` against routes, a
      browser tool for UI, with fixture data.