@bonesofspring/ai-rules 0.2.18 → 0.2.20

package/presets/cursor/java/rules/product-specs.mdc

@@ -13,6 +13,8 @@ Product page/feature **behavior** specs live under the consumer repo `docs/specs
 
 **Authoring** (Generate / Bootstrap modes, INDEX/frontmatter v1, body checklist, greenfield, conflict precedence) → load **`product-specs-authoring`** when generation is requested (`/spec-start`, brief AC, or router `spec-gen`).
 
+**Pipeline `specMode`:** `consume` (this stem) · `generate` (authoring stem) · `none` (spike/research — skip INDEX row requirement; do not invent a dummy INDEX). Primary field: `brief.md` `## Spec mode`; optional `pipeline.json` `specMode`.
+
 ## Modes (summary)
 
 | Mode | When | Behavior |
@@ -20,19 +22,21 @@ Product page/feature **behavior** specs live under the consumer repo `docs/specs
 | **Consume** (default) | INDEX exists or globs hit `docs/specs/**` without generate intent | Discover via INDEX; soft-fail on miss; **never invent** INDEX/specs |
 | **Generate** | Explicit generate intent / AC / `/spec-start` with existing tree | Create/update page/feature specs + INDEX from stated sources |
 | **Bootstrap** | Explicit bootstrap / `/spec-start` when tree absent | Create INDEX + templates + first domain spec |
+| **None** (`specMode: none`) | Spike / research / preset-only | Skip INDEX requirement and author mode; no dummy INDEX row |
 
 Greenfield: agents may create INDEX/specs **only** on explicit intent, AC, or `/spec-start`. Missing INDEX alone does **not** authorize inventing the tree.
 
 ## Presence policy
 
+- If `specMode` is **`none`** → do **not** require an INDEX row; continue from brief/AC. Do not invent INDEX.
 - If `docs/specs/INDEX.md` is **missing** → the tree is **optional** (greenfield OK for *consume*). Continue with code/brief discovery; do not invent an INDEX solely because this stem loaded.
-- If INDEX **exists** → it is the **required discovery path** for work that touches a listed page, feature, route, or alias.
+- If INDEX **exists** and `specMode` is not `none` → it is the **required discovery path** for work that touches a listed page, feature, route, or alias.
 
 ## Discovery algorithm
 
-1. Always start at `docs/specs/INDEX.md` when present.
+1. Always start at `docs/specs/INDEX.md` when present (skip when `specMode: none`).
 2. Resolve the entry by: route, stable `id`, PageName / alias, or domain folder.
-3. Read the linked page spec (and optional domain `feature.md` when the INDEX or page Related links it).
+3. Read the **linked page** spec and, when INDEX or page Related links it, the optional domain `feature.md`. Do **not** dump the whole `docs/specs/**` tree into the prompt — locator = those linked files.
 
 ## Miss policy (INDEX present, row or file missing)
 
@@ -54,10 +58,10 @@ Same-changeset INDEX updates, frontmatter v1, required body headings, templates,
 ## Related
 
 - `product-specs-authoring` — generation modes, contracts, self-check.
+- Skill `spec-discovery` — opt-in research-before-spec (author mode only; not default consume).
 - `reference-features` — code structure mirror (how to layout files), not product behavior.
 - Consumer `.ai/context/**` when present — review/domain glossary; cross-link, do not replace.
 
-
 ## Stack notes
 
 - `routes`: HTTP paths. `ui` / `store`: usually `[]` (or handler labels). `e2e`: integration/contract test paths.

package/presets/cursor/java/skills/README.md

@@ -1,5 +1,5 @@
 # Skills (preset java)
 
-8 skills: `feature-delivery`, `unit-testing`, `integration-testing`, `ci-investigation`, `debug-investigation`, `code-review`, `technical-retro`, `write-adr`.
+10 skills: `feature-delivery`, `spec-authoring`, `spec-discovery`, `unit-testing`, `integration-testing`, `ci-investigation`, `debug-investigation`, `code-review`, `technical-retro`, `write-adr`.
 
 No `playwright-e2e` / `xcuitest-e2e` / `react-performance`.

package/presets/cursor/java/skills/ci-investigation/SKILL.md

@@ -9,3 +9,10 @@ description: Investigates failing CI checks on PRs and branches — mvn/gradle t
 2. Reproduce locally with the same commands.
 3. Minimal fix; for ai-rules preset PRs run `yarn check:preset-structure`.
 4. Do not treat Playwright/xcodebuild/`lint:js` as default Java gates.
+
+## MCP usage
+
+Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
+
+If a Sentry/Datadog (or similar) MCP is ready and the task is a production error, event, or trace, use it. Do not invent telemetry.
+

package/presets/cursor/java/skills/code-review/SKILL.md

@@ -20,6 +20,13 @@ description: Reviews pull requests and branch diffs for Java hexagonal services
 
 Never require iOS/Next-only gates (XCUITest, Playwright, `lint:js`).
 
+## Receiving review feedback
+
+<!-- shared-core: review/receiving-code-review.md -->
+
+When **implementing** review comments (not when issuing them): verify each item against the codebase before changing code; do not perform agreement (`You're absolutely right!`). Unclear items → ask, do not guess.
+
 ## Design guidance
 
 - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
+For agent team tasks, write the review artifact and upsert the owned terminal receipt (`completed` or `changes_requested`); do not mutate `status.json`.

package/presets/cursor/java/skills/debug-investigation/SKILL.md

@@ -3,13 +3,49 @@ name: debug-investigation
 description: Investigates bugs, failing tests, and unexpected behavior in Java services with runtime evidence before applying minimal fixes. Use for bugfix tasks, debugger agent runs, or regressions.
 ---
 
-# Debug investigation (Java)
+<!-- shared-core: quality/debug-investigation.md -->
+
+# Debug investigation
+
+Stack-agnostic root-cause loop. Consumed by skill `debug-investigation` and agent `debugger`. Platform paths, MCP, and stack commands belong in adapter **Stack notes**.
+
+## When
+
+Any bug, test failure, build failure, or unexpected behavior — **before** proposing a fix.
+
+## Phases (in order)
+
+1. **Evidence** — reproduce, or collect the closest evidence (error output, failing test, logs, user steps).
+2. **Isolate** — expected vs actual in one sentence; smallest relevant slice of the codebase.
+3. **Root cause** — name the cause before editing. One hypothesis at a time; do not stack speculative fixes.
+4. **Minimal fix + verify** — smallest change that preserves architecture and public contracts. Add a regression test when the behavior is user-facing or likely to recur. Re-run the **failing** check first, then the relevant lint/type/test slice.
+
+## 3-fix architecture gate
+
+If **three** fix attempts fail, or the same symptom returns after two supposed fixes: **STOP**. Do not attempt fix #4. Escalate — the design is likely wrong (human partner or `solution-architect`). Chasing symptoms is the failure mode.
+
+## Do not
+
+- Broad refactor during a bugfix.
+- Fix only where the error surfaces if invalid data originates elsewhere.
+- Claim `fixApplied: true` without re-running the failing check (see `quality/verification-before-completion.md`).
+
+## Stack notes
+
+### Stack process
 
 1. Capture failing `mvn test` / `./gradlew test` / logs / stack traces.
 2. Hypothesize layer (domain vs adapter vs wiring).
 3. Minimal fix + regression test when appropriate.
 4. Document in `debug-report.md`.
 
-## Design guidance
+### MCP usage
+
+Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
+
+If a Sentry/Datadog (or similar) MCP is ready and the task is a production error, event, or trace, use it. Do not invent telemetry.
+
+
+### Design guidance
 
 - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/cursor/java/skills/feature-delivery/SKILL.md

@@ -24,7 +24,13 @@ Implement only the current AC / decomposition task. Clarify ambiguity before cod
 
 ## Handoff
 
-Summarize by layer + validation. Update `.cursor/team/tasks/<slug>/status.json`.
+Summarize by layer + validation. Agent team: upsert the owned terminal receipt in `artifact-manifest.json`; do not mutate `status.json`.
+
+
+## MCP usage
+
+Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
+
 
 ## Design guidance
 

package/presets/cursor/java/skills/spec-discovery/SKILL.md

@@ -0,0 +1,58 @@
+---
+name: spec-discovery
+description: Opt-in research-before-spec for task-analyst author mode. 11 named methods plus a mandatory claim ledger. Use when the user or AC asks discovery before generating docs/specs — not default /task consume.
+---
+
+# Spec discovery
+
+Requestable — **not** always-on. Load **only** in **task-analyst author mode** when the user or AC asks research-before-spec (including `/spec-start` with that intent). Never default consume `/task`. Not a pipeline step.
+
+Load **`product-specs`** (and **`product-specs-authoring`** after this skill if authoring follows). Do **not** invent product behavior. Do **not** create a second spec-file tree.
+
+## Load policy
+
+1. Pick a **subset** of methods that fit the task — not all 11 every time.
+2. **`claim-ledger` is mandatory** whenever this skill runs.
+3. Write chronological notes to `.cursor/team/tasks/<slug>/.memlog.md` (append-only). Do **not** mutate `status.json` / `metrics.json`.
+4. Discovery output lives in memlog + `brief.md` sections. Then hand off to skill **`spec-authoring`** (or stop if `specMode: none`).
+
+Backend / MCP stacks: skip UI-only examples; prefer `analog-scan`, `code-archaeology`, `problem-define`, `assumption-audit`, `claim-ledger`.
+
+## Methods
+
+| Method | Produces | Skip when |
+|--------|----------|-----------|
+| **intake-capture** | Raw idea, origin, first unknowns → memlog + brief Research inputs | User prompt + AC already complete |
+| **index-locator** | Related INDEX rows + linked spec paths + gaps | `specMode: none` or INDEX absent without consume intent |
+| **code-archaeology** | Observed behavior labeled `inferred`/`draft` with path citations | Greenfield with no relevant code |
+| **research-pack-scan** | Claims from `team/tasks/<slug>/research/**` or user-supplied paths | No research paths cited |
+| **evidence-against** | Reasons the idea may fail | Internal spike with no product/external risk |
+| **problem-define** | Who hurts, goals, non-goals, cost of inaction → brief | Brief Goal + Out of scope already exhaustive |
+| **concept-shape** | 2–3 approach options + appetite (small/medium/large); no API design | `architecture.md` exists or one obvious path |
+| **working-backwards-check** | Headline + 5 customer objections + verdict `forged` / `needs-heat` / `cracked` | Consume mode with approved specs |
+| **assumption-audit** | Assumption register → brief Assumptions + `open_questions` | Never skip in author mode (keep lightweight) |
+| **analog-scan** | 2–3 repo analogs via `reference-features` / code search | No plausible analog |
+| **claim-ledger** | Markdown table `source → claim` for every product-behavior claim | **Never skip** when this skill is loaded |
+
+## Claim ledger (required)
+
+Block spec authoring until every product-behavior claim has a source:
+
+```markdown
+| Source | Claim |
+|--------|-------|
+| brief AC-3 | Checkout shows empty cart copy |
+| code-archaeology inferred | Empty state uses an illustration |
+```
+
+Sources: AC / user / UI copy / labeled code inference / research path. Unsourced claims → `open_questions`.
+
+## Memlog
+
+Path: `.cursor/team/tasks/<slug>/.memlog.md`. Chronological `## YYYY-MM-DD` headings. Optional tags: `decision`, `assumption`, `override`, `event`, `claim`.
+
+## Forbidden
+
+- 108-technique catalogs, HTML composers, party-mode, five `assess.*` slash commands, Python memlog runtime.
+- Dummy INDEX rows when `specMode: none`.
+- Dumping the whole `docs/specs/**` tree — locator is INDEX → linked page + optional `feature.md`.

package/presets/cursor/java/team/README.md

@@ -13,6 +13,7 @@ Artifact directory for the agent-team pipeline for Java backends (hexagonal / po
     status.json
     brief.md
     decomposition.md
+    .memlog.md
     …
 ```
 
@@ -30,6 +31,13 @@ Artifact directory for the agent-team pipeline for Java backends (hexagonal / po
 
 Bootstrap `tasks/<slug>/` by **writing** artifacts (Write tool), not Shell `mkdir`. Cursor sandbox → `Operation not permitted` otherwise (worse on Desktop/Documents).
 
+
+## specMode, applyReadiness, memlog
+
+- **`specMode`:** `consume` | `generate` | `none` — primary in `brief.md` `## Spec mode`; optional top-level `pipeline.json` `specMode`. `none` skips INDEX/author mode (spike/research).
+- **`applyReadiness`:** YAML frontmatter on developer `implementation.md`; JSON-shaped `{ "state": "blocked"|"ready"|"all_done", "contextFiles": [] }` on the analyst receipt (analyst may emit `blocked` pre-gate). See `agent-artifact-contracts`.
+- **Memlog:** `.cursor/team/tasks/<slug>/.memlog.md` (Claude: `.claude/team/tasks/<slug>/.memlog.md`) — append-only, agent-written; `/task-continue` may read. Hook does not parse it. Example: `fixtures/memlog.example.md`.
+
 ## Artifact manifest and receipts
 
 Each slug stores one context index at `.cursor/team/tasks/<slug>/artifact-manifest.json`. Schema v1 is defined by shared core `agent-team/agent-artifact-contracts.md`: every entry declares its producer, status, authoritative paths, acceptance-criteria IDs, decomposition task IDs, timestamps, and a terminal completion receipt.

package/presets/cursor/java/team/fixtures/feature-full.json

@@ -1,20 +1,56 @@
 {
   "slug": "example-feature-full",
   "intent": "feature",
+  "specMode": "consume",
   "profile": "full",
   "summary": "Multi-layer Java use case with integration-test coverage",
   "steps": [
-    { "agent": "task-analyst", "label": "Clarify and decompose" },
-    { "agent": "solution-architect", "label": "Design boundaries", "model": "strong" },
-    { "agent": "feature-developer", "label": "Implement + unit tests", "scope": "unit-in-dev" },
-    { "agent": "build-verifier", "label": "mvn test / ./gradlew test / static analysis", "model": "cheap" },
-    { "agent": "security-reviewer", "label": "Security review", "model": "strong" },
-    { "agent": "code-reviewer", "label": "Code review", "model": "cheap" },
-    { "agent": "qa-tester", "label": "Integration tests", "scope": "e2e-only" },
-    { "agent": "integration-test-planner", "label": "Plan integration coverage" },
-    { "agent": "integration-test-generator", "label": "Generate integration tests" }
+    {
+      "agent": "task-analyst",
+      "label": "Clarify and decompose"
+    },
+    {
+      "agent": "solution-architect",
+      "label": "Design boundaries",
+      "model": "strong"
+    },
+    {
+      "agent": "feature-developer",
+      "label": "Implement + unit tests",
+      "scope": "unit-in-dev"
+    },
+    {
+      "agent": "build-verifier",
+      "label": "mvn test / ./gradlew test / static analysis",
+      "model": "cheap"
+    },
+    {
+      "agent": "security-reviewer",
+      "label": "Security review",
+      "model": "strong"
+    },
+    {
+      "agent": "code-reviewer",
+      "label": "Code review",
+      "model": "cheap"
+    },
+    {
+      "agent": "qa-tester",
+      "label": "Integration tests",
+      "scope": "e2e-only"
+    },
+    {
+      "agent": "integration-test-planner",
+      "label": "Plan integration coverage"
+    },
+    {
+      "agent": "integration-test-generator",
+      "label": "Generate integration tests"
+    }
+  ],
+  "humanGates": [
+    "after:task-analyst"
   ],
-  "humanGates": ["after:task-analyst"],
   "autoChain": true,
   "skipped": [
     {

package/presets/cursor/java/team/fixtures/memlog.example.md

@@ -0,0 +1,9 @@
+# Memlog example
+
+Append-only. Agents write; `/task-continue` may read. The hook does not parse this file.
+
+## 2026-08-13
+
+- `decision`: specMode=generate; research-before-spec requested
+- `claim`: empty-cart copy lives in the empty-state handler (code-archaeology, inferred)
+- `assumption`: no guest checkout in v1

package/presets/cursor/mcp-ts/MCP.md

@@ -34,4 +34,23 @@ Adjust `command`/`args` to the project's `bin` / `npx` entry after packaging. Pr
 
 Do not put secrets in the file. Optional: `CONTEXT7_API_KEY` in the environment.
 
-After init: Settings → MCP → enable servers. `init` overwrites the same-named MCP config.
+
+## Agent usage
+
+Load requestable rule `mcp-usage`. The **session MCP catalog** is source of truth (this file and `mcp.json` are hints). Discover tool schemas before calling; never invent them.
+
+**Context7 (shipped):** query docs when a third-party API is not confirmed by lockfile + sibling files. Use the installed major. Cap ≤3 doc queries per question. If Context7 is down, mark `// VERIFY` and continue — do not block.
+
+## Local overlay (not shipped)
+
+`init` **merges** `mcpServers`: preset keys are updated; extra local servers are kept. User-level MCP is never touched. Prefer user-level MCP if you do not want overlay servers in the project file.
+
+Use an overlay only when it is **ready** (`serverStatus` not `error` / `needsAuth` / `loading`) **and** the task fits. Absence is not a blocker unless the user required that MCP as source of truth.
+
+| Kind | Typical aliases | When |
+|------|-----------------|------|
+| Observability | `sentry`, `datadog`, `plugin-datadog-*` | production error, event/trace id, APM |
+| Tickets | `linear`, `jira`, `notion`, `plugin-notion-*` | ticket/page URL; read-only; task-folder artifacts remain SoT |
+| GitHub MCP | `github` | optional; native `gh` remains SoT for PRs and checks |
+
+Do **not** require Storybook, Playwright, or Chrome DevTools MCP as delivery gates on this preset.

package/presets/cursor/mcp-ts/agents/build-verifier.md

@@ -18,6 +18,12 @@ You are the build verifier for **TypeScript MCP servers** (and for **ai-rules pr
 
 **Never** require Playwright, XCUITest, `lint:js`/`lint:css`, `xcodebuild`/`SwiftLint`, or Go tools (`go test` / `go vet` / `golangci-lint`) as the MCP gate.
 
+## Verification before completion
+
+<!-- shared-core: quality/verification-before-completion.md -->
+
+Before writing `validation-report.md` or claiming PASS: IDENTIFY the commands, RUN them, READ exit codes, VERIFY they match the verdict, THEN claim. Do not mark PASS from memory of a prior developer run.
+
 ## Preset-structure validation (when editing `packages/ai-rules/presets/**`)
 
 From `packages/ai-rules/`:

package/presets/cursor/mcp-ts/agents/feature-developer.md

@@ -43,6 +43,13 @@ Implement MCP server features following **mcp-ts** boundaries.
 ## Design guidance / anti-sycophancy
 
 - Load `design-guidance` and `anti-sycophancy-discipline` when writing or changing code.
+- When acting on review feedback (`changes_requested` / human comments): verify each item against the codebase before implementing; no performative agreement.
+
+## Verification before completion
+
+<!-- shared-core: quality/verification-before-completion.md -->
+
+Before handoff, IDENTIFY→RUN→READ→VERIFY the scoped checks for this WP, THEN claim. Do not say the work is done without that evidence in the same turn. Full-project lint is `build-verifier`.
 
 
 ## Product specs (docs/specs)
@@ -52,6 +59,29 @@ When work touches a page/feature/route/alias: if `docs/specs/INDEX.md` exists (o
 Mechanical INDEX/frontmatter fixes only when implementation renames routes/ids. Substantive behavior edits → hand back to task-analyst (or tech-writer where present). If INDEX is absent and generation was not approved, treat specs as optional (greenfield).
 
 
+**specMode `none`:** do not require INDEX; implement from brief/AC only.
+
+**applyReadiness:** YAML frontmatter on `implementation.md`:
+
+```yaml
+applyReadiness:
+  state: ready   # blocked | ready | all_done
+  contextFiles: []
+```
+
+`blocked` if human gate pending, required spec missing, required UX `INCOMPLETE`, or incomplete WP deps. `ready` when the current WP may be implemented. `all_done` on the final receipt when mechanical spec sync is done.
+
+**Code Map + Suggested Review Order:** when this WP spans **>1 layer or module**, add to `implementation.md` a Code Map (3–8 annotated paths) and Suggested Review Order lines `concern | path:line | ≤15 words`. Omit for single-file / single-layer WPs.
+
+**Memlog:** append implementation decisions to `.cursor/team/tasks/<slug>/.memlog.md` (append-only).
+
+
+
+## MCP usage
+
+Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
+
+
 ## Artifact contract
 
 - **Authoritative inputs:** read `.cursor/team/tasks/<slug>/artifact-manifest.json` first; consume handoff `artifactInputIds` when supplied, otherwise consume the manifest entries for `brief.md`, `decomposition.md`, current scope, and applicable prior findings.

package/presets/cursor/mcp-ts/agents/solution-architect.md

@@ -21,3 +21,8 @@ Write `architecture.md` covering:
 - Follow `mcp-server-boundaries` and `mcp-tool-design`.
 - Do not invent SDK APIs — mark VERIFY or research via Context7.
 - Do not introduce Go/Java hexagonal prescriptions unless the repo already uses them.
+
+## MCP usage
+
+Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
+

package/presets/cursor/mcp-ts/agents/task-analyst.md

@@ -6,6 +6,16 @@ readonly: false
 
 Analyze MCP server work requests for the **mcp-ts** preset.
 
+## Classify first
+
+<!-- shared-core: agent-team/task-classification.md -->
+
+Before decomposing, name the class: **spike** / **bounded** / **architectural**. Maps to existing pipeline profiles — do not invent a second orchestrator.
+
+- **Spike** — research DoR; no implement tasks.
+- **Bounded** — few tasks, only layers actually touched; do not pad types/api/store/ui.
+- **Architectural** — full layer table; architect when boundaries are unclear.
+
 ## Deliverables
 
 1. `brief.md` — goal, AC, out of scope, assumptions, risks.
@@ -30,6 +40,15 @@ Analyze MCP server work requests for the **mcp-ts** preset.
 
 **Author mode (Generate / Bootstrap):** When the user runs `/spec-start`, router intent is `spec-gen` / bootstrap, or brief/AC requests generation: load **`product-specs`** + **`product-specs-authoring`** and skill **`spec-authoring`**. You are the **primary author** (INDEX bootstrap included). Follow frontmatter v1 + required headings; update INDEX in the **same change set**; default `status: draft`. Block handoff via `open_questions` until the authoring self-check passes.
 
+
+**Spec mode:** Write `## Spec mode` in `brief.md` with exactly one of `consume` | `generate` | `none`. Infer if unset: spike/research/preset-only → `none`; `/spec-start` or router `spec-gen` → `generate`; otherwise `consume`. Router may echo `specMode` on `pipeline.json`.
+
+**`none`:** skip INDEX row requirement and author mode; do not invent a dummy INDEX.
+
+**Research-before-spec (opt-in):** load skill **`spec-discovery`** only when the user/AC asks research before authoring (not default consume `/task`). Run a **subset** of methods; **`claim-ledger` is mandatory** whenever the skill loads. Append chronological notes to `.cursor/team/tasks/<slug>/.memlog.md` (append-only; do not mutate `status.json`).
+
+**applyReadiness (author blocked):** if specs are drafted but the human gate has not passed, or a required named spec is missing, emit `applyReadiness: { "state": "blocked", "contextFiles": ["…"] }` on the analysis receipt. Do not invoke feature-developer.
+
 ### Brief sections (when author mode or INDEX exists)
 
 Add to `brief.md`:
@@ -45,6 +64,14 @@ Add to `brief.md`:
 **mcp-ts:** no tech-writer — own Generate/Bootstrap **and** post-sync via docs-only / regenerate intents. Prefer `type: feature`; `routes` = tool names; `ui`/`store` = `[]`.
 
 
+
+## MCP usage
+
+Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
+
+If the prompt/brief has a tracker URL (Linear/Jira/Notion/…) and that MCP is ready, pull AC **read-only**. Task-folder artifacts remain SoT.
+
+
 ## Artifact contract
 
 - **Authoritative inputs:** read `.cursor/team/tasks/<slug>/artifact-manifest.json` first; consume `pipeline.json`, the manifest routing entry, user-approved decisions, and any authoritative architecture/approval entries.

package/presets/cursor/mcp-ts/agents/task-router.md

@@ -46,6 +46,20 @@ Append **`security-reviewer` after `build-verifier`** for `feature` / `bugfix` /
 
 **Never skip `build-verifier`** after developer when TypeScript sources changed.
 
+## Task class (spike / bounded / architectural)
+
+<!-- shared-core: agent-team/task-classification.md -->
+
+Name the class in `routingReasons`. Maps to profiles already in this file — do not add a parallel step table.
+
+| Class | Use existing |
+|-------|----------------|
+| Spike | intent `spike` |
+| Bounded | `profile: light` (or skip analyst when AC is complete) |
+| Architectural | `profile: full` + `solution-architect` when boundaries unclear |
+
+SoT: `agent-team/task-classification` (shared-core marker above; do not invent a second pipeline).
+
 ## Routing decision rubric
 
 Keep top-level `profile` and emit this top-level object in every new `pipeline.json`:
@@ -82,6 +96,7 @@ Fixtures: `.cursor/team/fixtures/` (feature-full, feature-light, bugfix-standard
 | Intent | Default humanGates |
 |--------|-------------------|
 | feature, refactor | `["after:task-analyst"]` |
+| spec-gen | `["after:task-analyst"]` |
 | spike | `["after:solution-architect"]` |
 | bugfix, review-only | `[]` |
 
@@ -104,6 +119,11 @@ Detect and set routing reasons when the user asks to **generate / bootstrap prod
 
 Do **not** add a dedicated `spec-author` agent. Do not require solution-architect for routine spec authoring.
 
+
+**specMode (optional `pipeline.json` field):** `none` for spike/research; `generate` for `spec-gen` / `/spec-start`; `consume` default when INDEX exists. Echo top-level `specMode`. Brief `## Spec mode` wins on conflict.
+
+Do **not** add a pipeline step for `spec-discovery`. Instruct analyst to load that skill only when the user/AC asks research-before-spec.
+
 ## Runtime initialization
 
 Return the routing receipt to the orchestrator. The orchestration runtime/hook exclusively initializes and updates `status.json`, `metrics.json`, attempt identities, and gate lifecycle; the router does not write those shared runtime files.

package/presets/cursor/mcp-ts/commands/spec-start.md

@@ -14,7 +14,7 @@ Routes intent **`spec-gen`** (or bootstrap) → **task-analyst** in **author mod
 3. Ensure `.cursor/team/tasks/<slug>/` exists (Write artifacts; not Shell mkdir).
 4. Write `.cursor/team/active-task.json` → `{ "slug": "<slug>" }`.
 5. Write minimal `pipeline.json`: task-analyst → (optional stop) → feature-developer only if user asked implement-after. **No separate spec-author agent.**
-6. Invoke **task-analyst** with: author mode; load **`product-specs`** + **`product-specs-authoring`** + skill **`spec-authoring`**; Bootstrap if `docs/specs/` absent, else Generate.
+6. Invoke **task-analyst** with: author mode; load **`product-specs`** + **`product-specs-authoring`** + skill **`spec-authoring`**; Bootstrap if `docs/specs/` absent, else Generate. Optional: if arguments/AC ask research-before-spec, also load skill **`spec-discovery`** (not default).
 7. Wait for analyst. **Do not** invoke feature-developer until human gate passes.
 
 ## Human gate

package/presets/cursor/mcp-ts/mcp.json

@@ -4,7 +4,7 @@
       "command": "npx",
       "args": [
         "-y",
-        "@upstash/context7-mcp@3.2.5"
+        "@upstash/context7-mcp@4.0.2"
       ]
     }
   }

package/presets/cursor/mcp-ts/rules/README.md

@@ -18,9 +18,9 @@
 ## Loading strategy
 
 - **`alwaysApply: true`** (Cursor) / **without `paths:`** (Claude) — base invariants only (**3**)
-- **On-demand / requestable** — MCP domain rules, tooling, security, tests, feature-delivery, agent-team, design-guidance, anti-sycophancy
+- **On-demand / requestable** — MCP domain rules, tooling, security, tests, feature-delivery, agent-team, design-guidance, mcp-usage, anti-sycophancy
 - **Preset author meta** (globs `packages/ai-rules/presets/**`, never alwaysApply): five `preset-*` wrappers
-- **Skills** — `feature-delivery`, `unit-testing`, `code-review`, `debug-investigation`
+- **Skills** — `feature-delivery`, `spec-discovery`, `unit-testing`, `code-review`, `debug-investigation`
 
 ### MCP edit bundles
 
@@ -39,6 +39,7 @@
 | `quality/code-quality-and-refactoring.md` | `code-quality-and-refactoring.mdc` | embed |
 | `quality/anti-sycophancy-discipline.md` | `anti-sycophancy-discipline.mdc` | embed |
 | `quality/design-guidance.md` | `design-guidance.mdc` | embed |
+| `quality/mcp-usage.md` | `mcp-usage.mdc` | embed | requestable Context7 + overlay MCP |
 | `agent-team/agent-team-orchestrator.md` | `agent-team-orchestrator.mdc` | lineage |
 | `agent-team/agent-team-intake.md` | `agent-team-intake.mdc` | embed |
 | `architecture/feature-delivery-workflow.md` | `feature-delivery-workflow.mdc` | lineage |

package/presets/cursor/mcp-ts/rules/agent-team-orchestrator.mdc

@@ -19,6 +19,7 @@ Work request without `/task` — see **agent-team-intake** (when to suggest the
 | `/task-continue <slug>` | After human gate or pause |
 | `/feature-start <desc>` | Legacy: analyst-only start (no router) |
 | `/feature-continue <slug>` | Alias of task-continue |
+| `/spec-start [desc]` | Generate/bootstrap `docs/specs` — router intent `spec-gen` → analyst author mode → human gate |
 | `/technical-retro [slug]` | Retro with agent team block |
 
 ## Roles (shared catalog)

package/presets/cursor/mcp-ts/rules/anti-sycophancy-discipline.mdc

@@ -12,7 +12,7 @@ alwaysApply: false
 
 Procedural rules for code generation and review. Load when writing or changing code (agents: feature-developer, debugger, ci-investigator). Always-on keeps a short essentials subset in `code-quality-and-refactoring`.
 
-1. **Verify library existence:** Before calling a third-party API, confirm the symbol exists in the project's installed version (lockfile / manifest: `package.json`, `go.mod`, `Podfile.lock`, `pom.xml`, `Cargo.toml`, or equivalent). If you cannot verify, mark `// VERIFY: lib.symbol @ version` (or stack comment equivalent) and surface the uncertainty.
+1. **Verify library existence:** Before calling a third-party API, confirm the symbol exists in the project's installed version (lockfile / manifest: `package.json`, `go.mod`, `Podfile.lock`, `pom.xml`, `Cargo.toml`, or equivalent). If that is not enough and Context7 MCP is available, load **`mcp-usage`** and query docs for the **installed major**. If you still cannot verify, mark `// VERIFY: lib.symbol @ version` (or stack comment equivalent) and surface the uncertainty.
 2. **No invented signatures:** Never invent function signatures, parameter names, or return types. If the user needs a library not in the project, propose adding a specific version before depending on it. Silent stubs are worse than refusal.
 3. **Enumerate edge cases before validating:** When asked "is this correct?" or "does this work?", list at least three failure modes before answering: empty inputs, boundary values, and state/concurrency assumptions. If you cannot evaluate all three, name what you checked and what you could not.
 4. **Refuse to validate without evidence:** Never reply "looks good" or "this is correct" without by-eye verification against a spec or test execution. If no spec exists, ask for one or refuse to validate.

package/presets/cursor/mcp-ts/rules/code-quality-and-refactoring.mdc

@@ -33,7 +33,7 @@ alwaysApply: true
 
 Essentials below. Full procedural set (~17 rules) → load **`anti-sycophancy-discipline`**.
 
-- Unverifiable third-party API → mark `// VERIFY: lib.symbol @ version` (or stack equivalent); never invent signatures.
+- Unverifiable third-party API → if Context7 is up, load **`mcp-usage`** and query the installed major; else mark `// VERIFY: lib.symbol @ version` (or stack equivalent); never invent signatures.
 - Before "is this correct?" — ≥3 failure modes (empty, boundary, concurrency/state) or name what you could not check.
 - Refactor without tests → propose characterization test; if declined, label `UNTESTED`.
 - Comments = WHY only when non-obvious; ban self-referential "added for issue Y".

package/presets/cursor/mcp-ts/rules/feature-delivery-workflow.mdc

@@ -15,7 +15,7 @@ Order of work:
 4. **Registration** — wire into server modules; keep entry (`src/index.ts`) free of tool business logic.
 5. **Tests** — unit + contract fixtures (`tests-unit`, `mcp-contract-testing`).
 6. **Package validation** — typecheck/test; optional Inspector smoke; `bin`/entry OK (`mcp-transport-packaging`).
-7. **Gate** — `post-change-test` (+ `mcp-ts-tooling`).
+7. **Gate** — `post-change-test` (+ `mcp-ts-tooling`). When the current WP spans **more than one** layer or module, `implementation.md` includes a **Code Map** (3–8 annotated paths) and **Suggested Review Order** (`concern | path:line | ≤15 word note`). Omit both for a single-file or single-layer WP.
 
 ```mermaid
 flowchart LR
@@ -41,6 +41,7 @@ flowchart LR
 - Monolithic `index.ts`; unscoped shell/FS tools; inventing SDK APIs; skipping schema tests "for speed".
 - Prescribing Go hexagonal folders or Next `app/src/**`.
 - Load `design-guidance` when assessing structure, smells, or pattern fit.
+- Do not mutate pipeline `status.json` / `metrics.json`; the orchestration hook is the single writer. Skills upsert the owned terminal receipt in `artifact-manifest.json`.
 
 ## Related