@brainervirus/workit-cursor 4.0.0 → 6.0.0

package/.cursor-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "workit",
   "displayName": "Workit",
   "description": "Adaptive Workit workflow with shared MCP tools and native Cursor hooks",
-  "version": "4.0.0",
+  "version": "6.0.0",
   "author": {
     "name": "Cristhofer Pincetti"
   },

package/README.md

@@ -45,13 +45,13 @@ npx @brainervirus/workit-cli init
 
 ## What it provides
 
-- MCP server exposing exactly the eight shared operation families: `workit_task`, `workit_policy`, `workit_evidence`, `workit_finding`, `workit_decision`, `workit_worker`, `workit_writer`, and `workit_state`.
+- MCP server exposing the seven shared operation families: `workit_task`, `workit_policy`, `workit_evidence`, `workit_finding`, `workit_decision`, `workit_worker`, and `workit_state` (read-only for unattested callers; mutations run through `node_modules/.bin/workit <family> <action> --json [--actor <session-id>]`).
 - One bounded native hook executable for session context, recognized product-write and shell interception, and native subagent lifecycle observations.
-- Sixteen canonical `workit-*` method skills and the `workit-contract` rule.
+- Eleven canonical `workit-*` method skills and the `workit-contract` rule.
 
 ## Host limitations
 
-Cursor maps shared Workit operations through the shared MCP transport. AskQuestion remains policy-only (`agent_guided`), session start and compaction are non-blocking, and arbitrary shell writes, Tab edits, and exact subagent stop identity are unavailable. Known Write/Edit/Delete targets are enforced only when the documented Cursor hook inputs prove them. Native subagent delegation is read-only for reviewer/investigator assignments; implementer delegation is unavailable because Cursor exposes no attested writer identity or stable child-stop identity.
+Cursor maps shared Workit operations through the shared MCP transport. AskQuestion remains policy-only (`agent_guided`), session start and compaction are non-blocking, and arbitrary shell writes, Tab edits, and exact subagent stop identity are unavailable. Known Write/Edit/Delete targets are enforced only when the documented Cursor hook inputs prove them. Native subagent delegation is read-only for reviewer/investigator assignments; implementer delegation is unavailable because Cursor exposes no stable child-stop identity.
 
 ## Configuration
 
@@ -59,7 +59,7 @@ Cursor maps shared Workit operations through the shared MCP transport. AskQuesti
 - MCP server: `mcp.json`.
 - Session-start hook: `hooks/hooks-cursor.json`.
 - Rule: `rules/workit-contract.mdc`.
-- Skills: `skills/` (sixteen canonical Workit methods).
+- Skills: `skills/` (eleven canonical Workit methods).
 
 ## Runtime
 
@@ -73,8 +73,8 @@ The runtime runs from `@latest` with `--prefer-online` and `--min-release-age=0`
 
 ## Capability boundaries
 
-- Authority-sensitive MCP mutations require an attested caller. A standalone or ordinary Cursor launch stays usable for read-only inspection and reports `capability_unavailable` for authority mutations.
-- Native hook enforcement is limited to documented inputs and blocking behavior. The plugin does not claim a `beforeMCPExecution` hook, cross-process receipts, delegation tokens, or automatic compaction restoration.
+- MCP is read-only for unattested callers: a standalone or ordinary Cursor launch stays usable for inspection and reports `capability_unavailable` for mutations, which run through the CLI instead.
+- Native hook enforcement is limited to documented inputs and blocking behavior. The plugin does not claim a `beforeMCPExecution` hook, delegation tokens, or automatic compaction restoration.
 
 ## Plugin layout
 
@@ -83,13 +83,13 @@ The runtime runs from `@latest` with `--prefer-online` and `--min-release-age=0`
 | `mcp/` + `dist/mcp-server.js` | MCP server entry (built).                                     |
 | `hooks/`                      | session-start hook manifest.                                  |
 | `rules/workit-contract.mdc`   | Adaptive task contract and truthful Cursor capability limits. |
-| `skills/`                     | Sixteen canonical adaptive Workit method skills.               |
+| `skills/`                     | Eleven canonical adaptive Workit method skills.               |
 | `.cursor-plugin/plugin.json`  | authoritative plugin manifest.                                |
 
 ## Package scripts
 
 ```bash
-  bun run build   # bundle MCP + native hook entries and copy sixteen method skills
+  bun run build   # bundle MCP + native hook entries and copy eleven method skills
 ```
 
 From the repository root, `bun run validate:cursor-marketplace` validates the tracked Marketplace artifact against the official Cursor JSON schemas and clean-checkout invariants (component paths, frontmatter, logo, sanitized vendor parity, no ignored-`dist` runtime references).

package/assets/templates/workit-contract.md

@@ -2,9 +2,10 @@
 
 Workit keeps one accountable lead and one shared task state. Inspect current
 task state before acting; use only the shared operations for task, policy,
-evidence, finding, decision, worker, writer, and state changes. Authority is
+evidence, finding, decision, worker, and state changes. Authority is
 bounded by the requested scope, current revision, caller/session provenance, and
-observed capabilities. Never claim host enforcement or evidence that the host
+observed capabilities; delivery is bounded by the workspace autonomy grants
+(`workit grant show`). Never claim host enforcement or evidence that the host
 cannot provide. Preserve unresolved requirements, gaps, and uncertain workers.
 
 Focused methods are loaded only when the resolved policy requires them. A method

package/commands/wk-bdd.md

@@ -1,7 +1,5 @@
 # /wk-bdd
 
-Load and apply the bundled `workit-bdd` skill to turn the requirement into Given/When/Then scenarios, agreed seams and test names.
-
-Write scenarios first, test at the highest agreed seam, run each slice RED then GREEN with `workit check test` (workit-behavioral-tdd), mock only at system boundaries, and take expected values from the scenario.
+Load and apply the bundled `workit-bdd` skill. Turn requirements into Given/When/Then scenarios, agree the test seam, and work test-first in vertical RED/GREEN slices. Use for BDD, TDD, acceptance criteria, scenarios, Given/When/Then, write a test first.
 
 Extra context: $ARGUMENTS

package/commands/wk-continue.md

@@ -0,0 +1,5 @@
+# /wk-continue
+
+Load and apply the bundled `workit-continue` skill. Keep work on track across interruptions and sessions - sort new input, checkpoint, hand off with a resume brief, and pick up by verifying inherited claims. Use for resume, pick up, handoff, new session, interruption, change of direction.
+
+Extra context: $ARGUMENTS

package/commands/wk-debug.md

@@ -1,7 +1,5 @@
 # /wk-debug
 
-Load and apply the bundled `workit-debug` skill to the failing behavior.
-
-Build a loop that goes red on the exact failure before hypothesizing, trace to the root cause, fix at the shared root, and leave a regression test at the seam.
+Load and apply the bundled `workit-debug` skill. Find a root cause before patching - start from a red-capable deterministic repro, rank hypotheses, bisect regressions, fix at the root with a regression test. Use for bug, broken, failing, flaky, regression, error, why does.
 
 Extra context: $ARGUMENTS

package/commands/wk-deslop.md

@@ -1,7 +1,5 @@
 # /wk-deslop
 
-Load and apply the bundled `workit-deslop` skill before opening a PR or after implementation.
-
-Remove AI slop from code and prose with a minimal diff: delete dead weight and filler, keep real symbol names and numbers, never refactor behavior.
+Load and apply the bundled `workit-deslop` skill. Remove AI slop before a PR - dead code, comments that restate the code, filler prose - with a minimal diff and identical behavior. Use for deslop, clean up, slop, tidy before PR, remove dead code, trim the PR body.
 
 Extra context: $ARGUMENTS

package/commands/wk-fanout.md

@@ -0,0 +1,5 @@
+# /wk-fanout
+
+Load and apply the bundled `workit-fanout` skill. Run independent slices in parallel - one worker per isolated worktree with a fixed brief and file-scope manifest, a non-author verifier per slice, results in the ledger. Use for fan out, parallelize, parallel agents, split the work, delegate, swarm.
+
+Extra context: $ARGUMENTS

package/commands/wk-implement.md

@@ -1,7 +1,5 @@
 # /wk-implement
 
-Load and apply the bundled `workit-implement` skill to carry out the scoped task.
-
-Implement the smallest change behind the agreed scope, verify behavior with the relevant checks, and reconcile task state, evidence, and findings when done.
+Load and apply the bundled `workit-implement` skill. Build a requested change in small verified steps - follow local patterns, run real checks with workit check, prove it on the running app, hand verification to a non-author. Use for implement, build, add a feature, make the change, code it.
 
 Extra context: $ARGUMENTS

package/commands/wk-review.md

@@ -1,7 +1,5 @@
 # /wk-review
 
-Load and apply the bundled `workit-review` skill to the current candidate.
-
-Review the real diff on two axes (standards + spec fidelity) with proof-required findings, then fix, dismiss with evidence, or escalate — never relabel self-review as independent.
+Load and apply the bundled `workit-review` skill. Independent review of a diff, branch or PR - intent fidelity and standards as separate axes, test quality, blast radius - recorded as a non-author verdict. Use for review, code review, check this PR or MR, is this safe, blast radius.
 
 Extra context: $ARGUMENTS

package/commands/wk-shape.md

@@ -0,0 +1,5 @@
+# /wk-shape
+
+Load and apply the bundled `workit-shape` skill. Shape work before building - brainstorm, grill open choices with a recommended answer, challenge weak premises, slice into PRs, propose a spec/ADR only when it pays. Use for brainstorm, plan, spec, design, options, should we, grill me.
+
+Extra context: $ARGUMENTS

package/commands/wk-ship.md

@@ -0,0 +1,5 @@
+# /wk-ship
+
+Load and apply the bundled `workit-ship` skill. Drive pushed work to its endpoint - open or stack PRs, fix red CI, answer PR threads, land verified PRs when granted. Use for ship, open a PR, babysit, CI failing, checks red, address comments, stack, merge, land.
+
+Extra context: $ARGUMENTS

package/commands/wk-test-audit.md

@@ -1,7 +1,5 @@
 # /wk-test-audit
 
-Load and apply the bundled `workit-test-audit` skill to find tautological and low-value tests.
-
-Run `workit test-audit`, triage each finding with "Name the Break" (replace with an independent oracle proven on a planted bug, keep with a reason, or remove only assertion-free/duplicate tests), check with `workit test-audit --mutate --diff`, and finish with `workit check test` green.
+Load and apply the bundled `workit-test-audit` skill. Find tautological, low-value or noisy tests and replace them with ones that catch real breaks. Use before trusting a green suite, for agent-written tests, test audit, tautology, weak tests, prune or strengthen tests.
 
 Extra context: $ARGUMENTS

package/commands/wk-verify-app.md

@@ -0,0 +1,5 @@
+# /wk-verify-app
+
+Load and apply the bundled `workit-verify-app` skill. Generate or maintain the project's own verify-<app> skill that launches, drives and observes the real app (CLI, web, API) so agents prove features work. Use for verify the app, run it, smoke test, prove it works, set up verification.
+
+Extra context: $ARGUMENTS