specweave 3.0.23 → 3.1.1

package/plugins/PLUGINS-INDEX.md

@@ -1,13 +1,13 @@
 # SpecWeave plugins index
 
-**Plugins**: 1 (`sw`) · **Skills**: 11 · **Commands**: 0 · **Hooks**: 2 default
+**Plugins**: 1 (`sw`) · **Skills**: 6 core + 5 optional · **Commands**: 0 · **Hooks**: 2 default
 
 The 1.x `commands/` namespace is gone: anything deterministic is a `specweave`
-CLI subcommand, and the model-judgement procedures are the 11 skills below.
+CLI subcommand, and the model-judgement procedures are the skills below.
 
 | Plugin | Triggers | Description |
 |---|---|---|
-| **specweave** (`sw`) | increment, spec, tasks, plan, implement, close, review, team, handoff, sync, GitHub, Jira, ADO, auto, brainstorm, qa, project, jev, system one | Increment lifecycle: plan → work the ledger → verify → review → complete, with cross-tool handoff, tracker sync and closed-set decisions delegated to Jev |
+| **specweave** (`sw`) | increment, spec, tasks, plan, implement, close, review, parallel, handoff, sync, GitHub, Jira, ADO, auto, grill me, glossary, ubiquitous language, project, jev, system one | Increment lifecycle: plan → work the ledger → verify → review → complete, with cross-tool handoff, tracker sync and closed-set decisions delegated to Jev |
 
 ## Quick lookup
 
@@ -17,13 +17,14 @@ CLI subcommand, and the model-judgement procedures are the 11 skills below.
 | "Implement" / "continue increment" | `sw:do` |
 | "We're done" / "close it" | `sw:done` |
 | "Review this" / "quality check" / "grill the code" | `sw:review` |
-| "Parallel agents" / "split this up" | `sw:team` |
+| "Parallel agents" / "split this up" | `sw:do` (parallel lanes) |
 | "Hand off" / "pick up" / "out of tokens" | `sw:handoff` |
-| "Push to GitHub" / "import issues" | `sw:sync` |
+| "Push to GitHub" / "import issues" (optional) | `sw:sync` |
 | "Run until done" | `sw:auto` |
-| "What are our options" | `sw:brainstorm` |
-| "Project brief" / "what is this project about" | `sw:project` |
-| "Jev" / "system one" / a decision whose answers can all be enumerated first | `sw:jev` |
+| "Grill me" / "interview me" (optional) | `sw:grill-me` |
+| "Glossary" / "what does Order mean here" (optional) | `sw:glossary` |
+| "Project brief" / "what is this project about" (optional) | `sw:project` |
+| "Jev" / "system one" / a decision whose answers can all be enumerated first (optional) | `sw:jev` |
 
 ## Hooks
 
@@ -34,10 +35,11 @@ Two by default, registered in `specweave/hooks/hooks.json` as exec-form
 `.specweave/state/jev-guard.enabled`, and a `PreToolUse` entry (matcher `Bash`) in that
 project's `.claude/settings.json`. `--no-guard-bash` removes all three.
 
-## Not in the plugin
+## Optional skills
 
-`tdd-cycle`, `e2e`, `debug`, `diagrams`, `release-expert` live in `skills-optional/`
-and install per-project with vskill. See `skills-optional/README.md`.
+`grill-me`, `glossary`, `sync`, `project` and `jev` ship in
+`plugins/specweave/skills-optional/` and install per project when enabled or detected:
+`specweave skills` lists them, `specweave skills enable <name>` turns one on.
 
 Deterministic operations are CLI: `specweave pickup | task | verify | complete |
-handoff | note | report | sync | doctor | jev`.
+handoff | note | report | sync | doctor | jev | skills | glossary | review`.

package/plugins/specweave/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "sw",
-  "description": "Portable intent and verified progress across coding tools. Eleven focused workflow skills, two default lifecycle hooks, and a deterministic CLI and live local dashboard.",
-  "version": "3.0.23",
+  "description": "Portable intent and verified progress across coding tools. Six core workflow skills plus opt-in grill-me, glossary, sync, project and jev, two default lifecycle hooks, and a deterministic CLI and live local dashboard.",
+  "version": "3.1.1",
   "author": {
     "name": "SpecWeave Team",
     "url": "https://spec-weave.com"

package/plugins/specweave/PLUGIN.md

@@ -1,6 +1,7 @@
 # SpecWeave plugin (`sw`)
 
-The Claude Code surface for SpecWeave: **11 skills, 2 default hooks, 1 closer agent**.
+The Claude Code surface for SpecWeave: **6 core skills, 5 optional skills, 2 default hooks,
+1 closer agent**.
 The skills are generated from `skills/sw-<name>/` at the repository root (the one source
 every tool shares); edit them there, never here.
 Everything deterministic lives in the `specweave` CLI; a skill exists only where a
@@ -8,23 +9,30 @@ procedure needs model judgement. There is no `commands/` namespace in 2.0.
 
 ## Skills
 
+Core, loaded by the plugin:
+
 | Skill | What it does |
 |---|---|
-| `sw:increment` | Plan a unit of work → one `spec.md` (Problem, Scope, ACs, Approach, Tasks) |
-| `sw:do` | Work the increment task by task through the ledger, with evidence per task |
-| `sw:done` | Close it: ledger check → `specweave verify` → optional review → `specweave complete` |
-| `sw:review` | Adversarial fresh-context review and quality check; every finding cites `path:line` |
-| `sw:team` | Several agents on one increment: a worktree each, claims through the ledger |
+| `sw:increment` | Settle the user's decisions, then plan one `spec.md` (Problem, Scope, ACs, Approach, Decisions, Tasks) |
+| `sw:do` | Work the increment task by task through the ledger, alone, unattended or in parallel lanes |
+| `sw:auto` | User-invoked entry to sw:do's unattended mode, driven by the Stop hook |
+| `sw:done` | Close it: ledger check → `specweave verify` → review → `specweave complete` |
+| `sw:review` | Adversarial review by a fresh context or another model family; every finding cites `path:line` |
 | `sw:handoff` | "Hand off" here, "pick up" in any other tool, account or machine |
-| `sw:sync` | GitHub / Jira / ADO: push, pull, status, setup |
-| `sw:auto` | Unattended loop driven by the Stop hook |
-| `sw:brainstorm` | Expand the option space before committing to one |
-| `sw:project` | Shared goal, memory, work items and briefs across tools |
-| `sw:jev` | Delegate closed-set decisions to Jev (TypeSafe System One): routing, command safety, screening |
 
-Optional procedures (tdd-cycle, e2e, debug, diagrams, release-expert) are **not** in the
-plugin — they ship from `skills-optional/` via
-`npx vskill install anton-abyzov/specweave/skills-optional/<name>`.
+Optional, shipped in `skills-optional/` and installed into a project as `sw-<name>` only
+when `.specweave/config.json` enables it (`specweave skills enable <name>`) or the project
+detects it:
+
+| Skill | What it does | Detected by |
+|---|---|---|
+| `sw:grill-me` | Interview the user in rounds until every decision is settled | `planning.deepInterview: deep` |
+| `sw:glossary` | GLOSSARY.md: each domain term across business, data, code and UI | `GLOSSARY.md` |
+| `sw:sync` | GitHub / Jira / ADO: push, pull, status, setup | a configured tracker |
+| `sw:project` | Shared goal, memory, work items and briefs across tools | `.specweave/project/hub.json` |
+| `sw:jev` | Delegate closed-set decisions to Jev (TypeSafe System One) | `jev.enabled` |
+
+`skills-catalog.json` is the list (generated from `skills/catalog.json`).
 
 ## Hooks
 
@@ -33,7 +41,7 @@ Two by default, both exec-form `node hooks/run.mjs <event>` (no shell, Windows-s
 | Hook | Job |
 |---|---|
 | `SessionStart` | Inject the active increment + next task as context |
-| `Stop` | Drive the `sw:auto` loop; `{}` for every ordinary session |
+| `Stop` | Drive the unattended loop (`sw:auto`); `{}` for every ordinary session |
 
 `PreToolUse` is **not** registered by default — `hooks.json` ships `SessionStart` and
 `Stop` only, exactly as in 2.1.0. `PreToolUse` and `PreCompact` stay callable
@@ -56,7 +64,7 @@ the marker and the project hook. This is a Claude Code surface only; other tools
 
 ## Requirements
 
-- Claude Code 2.1.0+, Node.js 18+, Git
+- Claude Code 2.1.0+, Node.js 20.12+, Git
 - The `specweave` CLI on PATH (`npm i -g specweave`). Skills degrade to documented
   manual steps when it is absent; they never silently no-op.
 

package/plugins/specweave/marketplace.json

@@ -1,18 +1,24 @@
 {
   "$schema": "https://spec-weave.com/schemas/skill-marketplace.v1.json",
   "plugin": "sw",
-  "description": "Skill catalog for the specweave plugin. The skills are generated from skills/sw-<name>/ (scripts/build/generate-skills.mjs); the plugin version is tracked in .claude-plugin/plugin.json.",
+  "description": "Skill catalog for the specweave plugin. The skills are generated from skills/sw-<name>/ and skills/catalog.json (scripts/build/generate-skills.mjs): core skills in skills/, optional ones in skills-optional/, installed per project by specweave skills enable or detection. The plugin version is tracked in .claude-plugin/plugin.json.",
   "skills": [
     {
       "name": "sw:increment",
       "path": "skills/increment/SKILL.md",
-      "description": "Plan a unit of work: one spec.md with Problem, Scope, numbered ACs, Approach and Tasks.",
+      "description": "Settle the user's critical decisions, then plan a unit of work: one spec.md with Problem, Scope, numbered ACs, Approach, Decisions and Tasks. Replaces brainstorm.",
       "deprecated": false
     },
     {
       "name": "sw:do",
       "path": "skills/do/SKILL.md",
-      "description": "Work the increment task by task through the ledger: task next, claim, implement, commit, task done with evidence.",
+      "description": "Work the increment task by task through the ledger, alone, unattended or in parallel lanes: task next, claim, implement, commit, task done with evidence. Replaces team.",
+      "deprecated": false
+    },
+    {
+      "name": "sw:auto",
+      "path": "skills/auto/SKILL.md",
+      "description": "User-invoked entry to sw:do unattended mode: run an increment until every task is done, then verify and close.",
       "deprecated": false
     },
     {
@@ -24,13 +30,7 @@
     {
       "name": "sw:review",
       "path": "skills/review/SKILL.md",
-      "description": "Adversarial fresh-context review and quality check; every finding cites path:line and is re-verified. Replaces qa, grill, code-reviewer and judge-llm.",
-      "deprecated": false
-    },
-    {
-      "name": "sw:team",
-      "path": "skills/team/SKILL.md",
-      "description": "Several agents on one increment: a worktree each, claims through the ledger, one closure. Replaces team-lead and team-merge.",
+      "description": "Adversarial review by a fresh context or another model family (specweave review); every finding cites path:line and is re-verified. Replaces qa, code-reviewer and judge-llm.",
       "deprecated": false
     },
     {
@@ -40,44 +40,49 @@
       "deprecated": false
     },
     {
-      "name": "sw:sync",
-      "path": "skills/sync/SKILL.md",
-      "description": "One sync surface for GitHub, Jira and Azure DevOps: push, pull, status, setup. Replaces the per-provider sync, mapper, validator and import skills.",
-      "deprecated": false
+      "name": "sw:grill-me",
+      "path": "skills-optional/grill-me/SKILL.md",
+      "description": "Interview the user in rounds until every decision in a plan is settled; records Decisions in spec.md.",
+      "deprecated": false,
+      "optional": true
     },
     {
-      "name": "sw:auto",
-      "path": "skills/auto/SKILL.md",
-      "description": "Run an increment unattended until every task is done, then verify and close.",
-      "deprecated": false
+      "name": "sw:glossary",
+      "path": "skills-optional/glossary/SKILL.md",
+      "description": "Build GLOSSARY.md: each domain term across business, data, code and UI; specweave glossary check finds drift.",
+      "deprecated": false,
+      "optional": true
     },
     {
-      "name": "sw:brainstorm",
-      "path": "skills/brainstorm/SKILL.md",
-      "description": "Expand the option space before committing to one, ending in a pick handed to sw:increment.",
-      "deprecated": false
+      "name": "sw:sync",
+      "path": "skills-optional/sync/SKILL.md",
+      "description": "One sync surface for GitHub, Jira and Azure DevOps: push, pull, status, setup. Replaces the per-provider sync, mapper, validator and import skills.",
+      "deprecated": false,
+      "optional": true
     },
     {
-      "name": "sw:jev",
-      "path": "skills/jev/SKILL.md",
-      "description": "Delegate closed-set decisions to Jev (TypeSafe System One) instead of a frontier turn: routing, command safety, text screening, failure triage.",
-      "deprecated": false
+      "name": "sw:project",
+      "path": "skills-optional/project/SKILL.md",
+      "deprecated": false,
+      "description": "Shared goal, memory, work items, artifacts and briefs, portable across AI tools and accounts.",
+      "optional": true
     },
     {
-      "name": "sw:project",
-      "path": "skills/project/SKILL.md",
+      "name": "sw:jev",
+      "path": "skills-optional/jev/SKILL.md",
+      "description": "Delegate closed-set decisions to Jev (TypeSafe System One) instead of a frontier turn: routing, command safety, text screening, failure triage.",
       "deprecated": false,
-      "description": "Shared goal, memory, work items, artifacts and briefs, portable across AI tools and accounts."
+      "optional": true
     }
   ],
   "optionalSkills": {
-    "note": "Not shipped in the plugin. Install with: npx vskill install anton-abyzov/specweave/skills-optional/<name>",
+    "note": "Shipped in plugins/specweave/skills-optional/, not loaded by the plugin. A project turns one on with: specweave skills enable <name>",
     "names": [
-      "tdd-cycle",
-      "e2e",
-      "debug",
-      "diagrams",
-      "release-expert"
+      "grill-me",
+      "glossary",
+      "sync",
+      "project",
+      "jev"
     ]
   },
   "removedIn2_0": {
@@ -87,9 +92,9 @@
       "sw:code-reviewer": "sw:review",
       "sw:judge-llm": "sw:review",
       "sw:pr-review": "sw:review",
-      "sw:team-lead": "sw:team",
-      "sw:team-merge": "sw:team",
-      "sw:team-build": "sw:team",
+      "sw:team-lead": "sw:do",
+      "sw:team-merge": "sw:do",
+      "sw:team-build": "sw:do",
       "sw:plan": "sw:increment",
       "sw:pm": "sw:increment",
       "sw:architect": "sw:increment",
@@ -132,5 +137,19 @@
       "sw:task": "sw:do",
       "sw-task": "sw-do"
     }
+  },
+  "removedIn3_1": {
+    "note": "Removed in 3.1. Use the replacement; there is no alias routing.",
+    "map": {
+      "sw:team": "sw:do",
+      "sw-team": "sw-do",
+      "sw:brainstorm": "sw:grill-me",
+      "sw-brainstorm": "sw-grill-me",
+      "skills-optional/tdd-cycle": "mattpocock/skills tdd",
+      "skills-optional/debug": "mattpocock/skills diagnosing-bugs",
+      "skills-optional/e2e": "sw:do (check each AC end to end)",
+      "skills-optional/diagrams": "none",
+      "skills-optional/release-expert": "none"
+    }
   }
 }

package/plugins/specweave/skills/auto/SKILL.md

@@ -1,48 +1,18 @@
 ---
-description: Run a SpecWeave increment unattended until every task is done, then verify and close. Use for "auto mode", "run until done", "ship this while I sleep".
+description: Run a SpecWeave increment unattended until every task is done, then verify and close - the Unattended section of sw-do. Use for "auto mode", "run until done".
 argument-hint: "[increment-ids...] [--dry-run|--reset]"
-version: 3.0.0
+disable-model-invocation: true
+version: 3.1.0
 ---
 <!-- Generated from skills/sw-auto/SKILL.md by scripts/build/generate-skills.mjs. Edit the source, then npm run build. -->
 
 # sw-auto: run until done
 
-Auto mode is the sw-do loop without stopping to ask. The bar does not drop: claim
-before editing, a passing test for every `done`, verify before closing.
-
-## Start
-
-1. The spec has nothing under `## Decisions` > `### Open` (or old `## Open questions`)
-   and every task has `Files` and a `Test`. If not, fix the spec first.
-2. `specweave auto 0042` records the session (`--dry-run` previews it, `--reset` clears
-   stale state). In a tool that runs SpecWeave's Stop hook (Claude Code with the `sw`
-   plugin) the hook hands you the remaining work after every turn until nothing is
-   left. In any other tool, nothing feeds you back: keep looping yourself.
-3. `specweave auto-status` shows progress; `specweave cancel-auto` stops it.
-
-## Each turn
-
-1. `specweave task next` → `specweave task claim T-NN` → implement inside its `Files` →
-   commit `0042: ...` → `specweave task done T-NN --run "<Test>"`.
-2. A failing test is fixed in the next turn, never marked done.
-3. Genuinely blocked (missing secret, ambiguous spec, external dependency):
-   `specweave task block T-NN --reason "<what is missing>"` and move on. Blocked tasks
-   still count as work left: when only blocked tasks remain, run `specweave cancel-auto`
-   and tell the user what each one needs, instead of looping until the turn limit.
-4. Nothing claimable left: run sw-done (verify, review, complete).
-
-## Running out of budget
-
-Before the session ends for tokens or time: `specweave handoff --reason "auto: out of
-tokens"`. The next session, in any tool or account, says "pick up" and continues.
+Follow sw-do's "Unattended (auto mode)" section for the increments named, starting
+with `specweave auto <ids>`, and close with sw-done when nothing claimable is left.
+This entry exists so the command keeps its name; sw-do holds the rules.
 
 ## Manual path (no CLI)
 
-Without the CLI there is no hook and no session file: follow the manual path of sw-do
-in a loop until every task in spec.md has a `done` or `skip` line, then sw-done.
-
-## Rules
-
-- Never edit `.specweave/state/auto-mode.json` by hand; `specweave auto --reset` clears it.
-- One auto session per project; check `specweave auto-status` before starting another.
-- Never widen a task's `Files` or weaken a test to keep the loop moving.
+Without the CLI there is no hook and no session file: follow sw-do's manual path in a
+loop until every task in spec.md has a `done` or `skip` line, then sw-done.

package/plugins/specweave/skills/auto/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "SpecWeave auto"
+  short_description: "Run an increment unattended until done"
+policy:
+  allow_implicit_invocation: false

package/plugins/specweave/skills/do/SKILL.md

@@ -1,7 +1,7 @@
 ---
-description: Work a SpecWeave increment task by task - claim, implement inside the task's Files, test, commit, done with evidence - then verify and close. Use for "implement", "continue", "keep going".
-argument-hint: "[increment-id]"
-version: 3.0.0
+description: Work a SpecWeave increment task by task - claim, implement inside its Files, test, commit, done with evidence - alone, unattended or in lanes, then close. Use for "implement", "continue", "auto".
+argument-hint: "[increment-id] [--auto] [--lanes]"
+version: 3.1.0
 ---
 <!-- Generated from skills/sw-do/SKILL.md by scripts/build/generate-skills.mjs. Edit the source, then npm run build. -->
 
@@ -19,23 +19,57 @@ hold, and notes left for you. No increment yet? Run sw-increment first.
 ## The loop
 
 1. `specweave task next` prints the next claimable task with its AC text.
-2. `specweave task claim T-03`. Exit 3: someone holds it; 4: its Files overlap a live
-   claim; 6: its dependencies are not done. Pick another. Never edit before claiming.
+2. `specweave task claim T-03`. Exit 3: someone holds it (your own earlier claim from
+   a crashed session: say so, then `--force`); 4: its Files overlap a live claim;
+   6: its dependencies are not done. Otherwise pick another. Never edit before claiming.
 3. Implement inside that task's `Files` only. Need another file? Claim the task that
-   owns it, or add a task to spec.md `## Tasks`.
+   owns it, or add a task to spec.md `## Tasks`. Use the words in `GLOSSARY.md`, if
+   the project has one, for every new name.
 4. Run the task's `Test`. Red means fix the code; never skip, weaken or delete a test.
    Don't write tests first or add unit tests the task did not ask for (unless the
    project's `testing` config or conventions require them): check the AC end to end,
    the way a user would hit it.
 5. Commit with the increment id first: `git commit -m "0042: fold the ledger"`.
-6. `specweave task done T-03 --run "npm run test:e2e -- double-claim"`. Exit 5: the command failed and
-   the task stays open. No `Test`? `--evidence "<sha> + what you checked"`.
+6. `specweave task done T-03 --run "npm run test:e2e -- double-claim"`. Exit 5: the
+   command failed and the task stays open. No `Test`? `--evidence "<sha> + what you checked"`.
 7. Stuck: `specweave task block T-03 --reason "<what is missing>"`. Not needed:
    `specweave task skip T-03 --reason "<why>"`. Then back to 1.
 
 Commands take the increment id last (`specweave task next 0042`) when more than one
 increment is active. `specweave task list` shows the whole board.
 
+## Unattended (auto mode)
+
+"Auto", "run until done", "ship this while I sleep": the same loop without stopping
+to ask. The bar does not drop.
+
+1. Start only when the spec has nothing under `## Decisions` > `### Open` and every
+   task has `Files` and a `Test`; otherwise fix the spec first.
+2. `specweave auto 0042` records the session (`--dry-run` previews, `--reset` clears
+   stale state). A tool that runs SpecWeave's Stop hook hands you the remaining work
+   after every turn; in any other tool, keep looping yourself.
+3. Blocked (missing secret, ambiguous spec, outside dependency): `task block` and move
+   on. When only blocked tasks remain, `specweave cancel-auto` and tell the user what
+   each one needs, instead of looping to the turn limit.
+4. `specweave auto-status` shows progress; one auto session per project.
+
+## Parallel lanes
+
+Three or more disjoint lanes, or 15+ tasks: you are the lead. Split, start, watch,
+merge and close; do not implement.
+
+1. Group tasks into 2 to 5 lanes whose `Files` do not overlap. Shared contracts
+   (types, schema) go in an early task the others list under `**Dependencies**: T-01`.
+2. One worktree and branch per lane agent (your tool's or app's worktree feature, or
+   `git worktree add ../0042-api -b inc/0042-api`), with `SPECWEAVE_AGENT=api` set.
+   Brief each one: its tasks, this loop, "edit only their Files", and on finish
+   `specweave task release --all-mine` plus `specweave note "api: done" 0042`.
+3. Watch with `specweave task list 0042`; `blocked` rows are your queue. A claim older
+   than 2 hours with no progress may be taken with `--force`.
+4. Merge the lane branches in dependency order (keep every `ledger.jsonl` line from both
+   sides), then close as below. Lane agents never run `specweave handoff`.
+   `specweave team` opens agent panes for the same setup in tools that have them.
+
 ## Finish without asking
 
 When `task next` has nothing left, run sw-done: verify, review, complete.
@@ -66,11 +100,13 @@ PowerShell never uses `>>` here: it writes UTF-16 and every other tool fails to
 Events: `claim`, `done` (needs `evidence`), `release`, `block` and `skip` (both need
 `note`), for example
 `{"t":"T-02","e":"skip","by":"codex@mbp","at":"2026-09-02T12:00:00Z","note":"covered by T-01"}`.
-`by` is `SPECWEAVE_AGENT` if set, else `<tool>@<host>`.
+`by` is `SPECWEAVE_AGENT` if set, else `<tool>@<host>`. Unattended or in lanes, follow
+the same steps by hand: there is no hook and no session file.
 
 ## Rules
 
 - A claim older than 2 hours with no `done` is stale and may be taken over.
 - Append only: never edit, reorder or delete a ledger line. On a merge conflict in
   `ledger.jsonl` keep every line from both sides.
-- Several agents on one increment: one worktree and branch each (sw-team).
+- Never widen a task's `Files` or weaken a test to keep a loop moving.
+- Never edit `.specweave/state/auto-mode.json` by hand; `specweave auto --reset` clears it.

package/plugins/specweave/skills/done/SKILL.md

@@ -1,7 +1,7 @@
 ---
 description: Close a SpecWeave increment - every task done or skipped, specweave verify green, a fresh-context review, then specweave complete. Use for "close it", "we are done", "finish up".
 argument-hint: "[increment-id] [--reason \"...\"]"
-version: 3.0.0
+version: 3.1.0
 ---
 <!-- Generated from skills/sw-done/SKILL.md by scripts/build/generate-skills.mjs. Edit the source, then npm run build. -->
 
@@ -19,8 +19,11 @@ Closing is verify, review, complete. The one hard gate is a passing
    against the ledger (an AC is met when all its tasks are done) and writes
    `reports/verify.md` and `reports/verify.json`. Red: fix and re-run. Do not tick
    AC boxes; they are derived.
-3. **Review.** For anything that ships, run sw-review in a fresh context. Fix critical
-   and high findings, then verify again.
+3. **Review.** For anything that ships, run sw-review in a fresh context. With
+   `review.crossModel` on, also `specweave review`: another model family reviews the
+   diff (exit 3 means fix first). If the project has a `GLOSSARY.md`, run
+   `specweave glossary check` and rename new code that uses an avoided word. Fix
+   critical and high findings, then verify again.
 4. **Docs.** If commands, config or user-facing behaviour changed, update README,
    CHANGELOG and the `## Commands` table in AGENTS.md in the same branch.
 5. **Complete.** `specweave complete 0042`. It refuses without a passing verify unless

package/plugins/specweave/skills/increment/SKILL.md

@@ -1,7 +1,7 @@
 ---
 description: Plan work as a SpecWeave increment - one spec.md with Problem, Scope, numbered ACs, Approach and Tasks - before writing code. Use for "plan a feature", "new increment", "let's build X".
 argument-hint: "\"<title>\" [--supersedes NNNN]"
-version: 3.0.0
+version: 3.1.0
 ---
 <!-- Generated from skills/sw-increment/SKILL.md by scripts/build/generate-skills.mjs. Edit the source, then npm run build. -->
 
@@ -17,18 +17,27 @@ and one PR.
 - A small self-contained fix needs no increment. Just do it.
 - An open increment already owns the files this touches (`specweave task list`)? Add
   ACs and tasks to its spec.md instead of opening another.
-- Read the code the change touches before writing Approach.
-- Unsure what to build at all? Run sw-brainstorm's Options first.
+- Read the code the change touches before writing Approach. If `GLOSSARY.md` exists,
+  write the spec in its terms.
+- Unsure what to build at all, or the user says "grill me": run sw-grill-me first
+  (`specweave skills enable grill-me` installs it).
 
 ## Decide
 
-Run sw-brainstorm's Decide step before writing ACs: think first, settle facts yourself,
-then ask the user only the decisions that are theirs, one question at a time, each with
-a recommended answer. `planning.deepInterview` sets the depth: `critical` (default) asks
-at most 5, `deep` ("grill me") has no cap, `off` skips. A clear request asks nothing.
-Record every answer and default in spec.md `## Decisions` and apply it to Scope, ACs
-and Approach. Without sw-brainstorm installed: ask at most 5, each with your
-recommendation, and record them the same way.
+Intent first: settle what the user wants and how a machine will check it before
+writing ACs. `planning.deepInterview` sets the depth: `critical` (default) as below,
+`deep` runs sw-grill-me, `off` states defaults and asks nothing.
+
+1. **Think first.** Read the code and config; settle every fact yourself.
+2. **Triage** each open decision: *fact* (look it up, never ask), *my call*
+   (reversible or low impact: pick a default), *theirs* (hard to reverse, costly, taste).
+3. **Ask** only "theirs", at most 5, highest impact first. Each gets one clause on why
+   it matters and 2 to 4 options, your recommendation first; "yes" accepts it. Use your
+   tool's structured question tool when it has one. A clear request asks nothing.
+4. **Record** in `## Decisions`: Asked, Defaulted (list every default: one the user
+   never saw is one they could not reject) and Open. Keep a line only when a later
+   change could contradict it: hard to reverse, surprising without context, or a real
+   trade-off. Apply each answer to Scope, ACs and Approach.
 
 ## Create it
 
@@ -98,4 +107,4 @@ Files that change and in what order, decisions, rejected alternatives, risks.
 ## Then
 
 Show the ACs and tasks. Unless the user asked to review the plan first, carry on with
-sw-do (one agent) or sw-team (three or more disjoint lanes).
+sw-do (one agent, or parallel lanes for three or more disjoint groups of tasks).

package/plugins/specweave/skills/review/SKILL.md

@@ -1,7 +1,7 @@
 ---
-description: Adversarial fresh-context review and risk check of an increment before it ships; every finding cites path:line and is re-verified. Use for "review", "qa", "quality check", "critique this".
+description: Adversarial review of an increment before it ships, by a fresh context or another model family; every finding cites path:line and is re-verified. Use for "review", "qa", "critique this".
 argument-hint: "[increment-id] [--full]"
-version: 3.0.0
+version: 3.1.0
 ---
 <!-- Generated from skills/sw-review/SKILL.md by scripts/build/generate-skills.mjs. Edit the source, then npm run build. -->
 
@@ -14,8 +14,8 @@ This is also the quality check: its verdict says whether the increment is ready.
 ## Non-negotiables
 
 - **Fresh context.** The session that wrote the code never approves it. Use a new
-  session, or a subagent if your tool supports them. If you wrote this code here and
-  cannot get a fresh context, say so in the report.
+  session, a subagent if your tool supports them, or another model (below). If you
+  wrote this code here and cannot get a fresh context, say so in the report.
 - **Every finding cites `path:line`** and a concrete failure: input or state leads to
   wrong output, a crash, a hang, data loss or a leak. "Consider refactoring" is not one.
 - **Re-verify.** Re-open the lines and, where a test can show it, run one. Drop what
@@ -42,6 +42,24 @@ This is also the quality check: its verdict says whether the increment is ready.
    (`### T-09 Fix empty evidence` + `- AC: AC-02 | Files: ... | Test: ...`) for sw-do, or
    is fixed and re-tested now. Then verify again and close with sw-done.
 
+## Another model
+
+A model reviewing code its own family wrote shares that code's blind spots.
+`specweave review` hands the increment to a reviewer from another family: it reads who
+finished the tasks from the ledger (`claude@mbp` is Claude), runs Codex with GPT-6.1-Sol
+on Claude-written code (Claude Opus on OpenAI-written code), and writes
+`reports/review-codex.md` in the shape below plus a ledger note. Exit 0: ship; 3: fix
+first, or no verdict; 1: no reviewer installed, or it failed.
+
+- Run it when `review.crossModel` is true in `.specweave/config.json`, when the user
+  asks for another model, or when you wrote the code and have no fresh context.
+- `--brief` prints the brief (ACs, tasks and their Files, the diff) to paste into any
+  model by hand; `--reviewer claude`, `--base origin/main` and `--timeout 45` override.
+- `review.reviewer` pins one reviewer; `review.reviewers.<name>.command` adds a CLI that
+  reads the brief on stdin and answers on stdout, or into `{out}` when it names one.
+
+Its findings get the same treatment as yours: re-open each line before acting on it.
+
 ## reports/review.md
 
 ```markdown
@@ -57,6 +75,7 @@ Nits: naming in ledger.ts:31.
 ```
 
 Verdict is `fix first` while any critical or high finding survives, else `ship`.
+`specweave complete` notes a `fix first` verdict in the newest review report.
 
 ## Manual path (no CLI)
 

package/plugins/specweave/skills-catalog.json

@@ -0,0 +1,32 @@
+{
+  "$comment": "The one list of SpecWeave skills. Core skills ship in the sw plugin and in every project. Optional skills install into a project only when listed under skills.enabled in .specweave/config.json, or when their detect rule matches and they are not under skills.disabled. Retired skills are removed from projects on update. scripts/build/generate-skills.mjs copies this file to plugins/specweave/skills-catalog.json.",
+  "core": ["increment", "do", "auto", "done", "review", "handoff"],
+  "optional": [
+    {
+      "name": "grill-me",
+      "summary": "Interview you in rounds until every decision in a plan is settled",
+      "detect": "deep-interview"
+    },
+    {
+      "name": "glossary",
+      "summary": "Build GLOSSARY.md: each domain term across business, data, code and UI",
+      "detect": "glossary-file"
+    },
+    {
+      "name": "sync",
+      "summary": "Push progress to and pull issues from GitHub, Jira or Azure DevOps",
+      "detect": "tracker"
+    },
+    {
+      "name": "project",
+      "summary": "Shared goal, work items and briefs in .specweave/project/hub.json",
+      "detect": "hub"
+    },
+    {
+      "name": "jev",
+      "summary": "Closed-set decisions through Jev (System One)",
+      "detect": "jev"
+    }
+  ],
+  "retired": ["qa", "task", "brainstorm", "team"]
+}