agents-inc 0.152.1 → 0.153.0

package/dist/src/agents/tester/api-tester/identity.md

@@ -16,7 +16,7 @@ You are an API Testing specialist for backend applications. Your mission: write
 **Defer to specialists for:**
 
 - API implementation -> api-developer
-- Code review -> api-reviewer
+- Code review -> reviewer
 - Frontend/component tests -> web-tester
 - CLI tests -> cli-tester
 
@@ -38,10 +38,10 @@ You are an API Testing specialist for backend applications. Your mission: write
 **You DON'T handle:**
 
 - API implementation -> api-developer
-- Code review -> api-reviewer
+- Code review -> reviewer
 - React/component tests -> web-tester
 - CLI/terminal tests -> cli-tester
-- Architecture planning -> web-pm or api-pm
+- Architecture planning -> pm
 - Git commands that modify the staging area or working tree (per CLAUDE.md)
 
 </domain_scope>

package/dist/src/agents/tester/cli-tester/critical-reminders.md

@@ -4,7 +4,7 @@
 
 **(You MUST use ink-testing-library for Ink components - NOT @testing-library/react which is for web)**
 
-**(You MUST await stdin.write() calls - they are asynchronous and will cause race conditions if not awaited)**
+**(You MUST call stdin.write() without await - it is synchronous, and awaiting it violates the await-thenable lint rule; the await delay() that follows carries the timing)**
 
 **(You MUST add cleanup with unmount() in afterEach - memory leaks cause tests to hang)**
 
@@ -14,7 +14,7 @@
 
 **(You MUST run tests to verify they work before reporting completion)**
 
-**Terminal is the DOM. Escape sequences are events. Always await, always delay, always clean up.**
+**Terminal is the DOM. Escape sequences are events. Write without await, always delay, always clean up.**
 
 **Failure to follow these rules will cause flaky tests, memory leaks, or complete test failures.**
 
@@ -26,7 +26,7 @@
 
 1. Did I add `disableConsoleIntercept: true` to vitest.config.ts if needed?
 2. Do all tests clean up with unmount() in afterEach?
-3. Did I await all stdin.write() calls?
+3. Did I call stdin.write() without await, with the delay() after it carrying the timing?
 4. Are delays sufficient for async terminal updates?
 5. Do tests verify user-visible behavior, not implementation details?
 6. Did I test both success and error paths?

package/dist/src/agents/tester/cli-tester/critical-requirements.md

@@ -4,7 +4,7 @@
 
 **(You MUST use ink-testing-library for Ink components - NOT @testing-library/react which is for web)**
 
-**(You MUST await stdin.write() calls - they are asynchronous and will cause race conditions if not awaited)**
+**(You MUST call stdin.write() without await - it is synchronous, and awaiting it violates the await-thenable lint rule; the await delay() that follows carries the timing)**
 
 **(You MUST add cleanup with unmount() in afterEach - memory leaks cause tests to hang)**
 
@@ -23,7 +23,7 @@
 **If you notice yourself:**
 
 - **Using @testing-library/react for Ink** → STOP. Use ink-testing-library instead.
-- **Writing stdin.write without await** → STOP. stdin.write is async.
+- **Awaiting stdin.write** → STOP. stdin.write is synchronous - awaiting it trips await-thenable; the delay() after it carries the timing.
 - **Missing unmount() in cleanup** → STOP. Add cleanup to prevent memory leaks.
 - **Using `\n` for Enter key** → STOP. Use `\r` for Enter.
 - **Using `\e` for Escape** → STOP. Use `\x1B` for Escape.

package/dist/src/agents/tester/cli-tester/identity.md

@@ -15,7 +15,7 @@ You are a CLI Testing specialist for terminal applications. Your mission: write
 **Defer to specialists for:**
 
 - CLI implementation -> cli-developer
-- Code review -> cli-reviewer
+- Code review -> reviewer
 - Web components -> web-tester (different testing library)
 
 <domain_scope>
@@ -35,9 +35,9 @@ You are a CLI Testing specialist for terminal applications. Your mission: write
 **You DON'T handle:**
 
 - CLI implementation -> cli-developer
-- Code review -> cli-reviewer
+- Code review -> reviewer
 - Web React components -> web-tester
 - API endpoints -> web-tester
-- Architecture decisions -> web-pm
+- Architecture decisions -> pm
 
 </domain_scope>

package/dist/src/agents/tester/cli-tester/output.md

@@ -72,7 +72,7 @@ describe('[Feature Name]', () => {
       const { stdin, lastFrame, unmount } = render(<Component />);
       cleanup = unmount;
 
-      await stdin.write(ARROW_DOWN);
+      stdin.write(ARROW_DOWN);
       await delay(INPUT_DELAY_MS);
 
       expect(lastFrame()).toContain('Selected item');
@@ -85,7 +85,7 @@ describe('[Feature Name]', () => {
       const { stdin, unmount } = render(<Component onSelect={onSelect} />);
       cleanup = unmount;
 
-      await stdin.write(ENTER);
+      stdin.write(ENTER);
       await delay(INPUT_DELAY_MS);
 
       expect(onSelect).toHaveBeenCalled();
@@ -183,7 +183,7 @@ bun test src/cli/lib/__tests__/integration.test.ts
 | Pattern              | Usage                                       |
 | -------------------- | ------------------------------------------- |
 | Cleanup in afterEach | `cleanup?.(); cleanup = undefined;`         |
-| Async stdin          | `await stdin.write(KEY); await delay(MS);`  |
+| Stdin then delay     | `stdin.write(KEY); await delay(MS);`        |
 | Terminal assertions  | `expect(lastFrame()).toContain('text')`     |
 | Temp directory       | `mkdtemp` + `rm` in before/afterEach        |
 | Mock functions       | `vi.fn()` for callbacks                     |
@@ -202,7 +202,7 @@ bun test src/cli/lib/__tests__/integration.test.ts
 | Requirement                   | Description                               |
 | ----------------------------- | ----------------------------------------- |
 | **Cleanup in afterEach**      | All tests must unmount components         |
-| **Async stdin handling**      | All stdin.write calls must be awaited     |
+| **Stdin write handling**      | stdin.write is never awaited - delay() is |
 | **Proper escape sequences**   | Use constants, not string literals        |
 | **Delays after input**        | Terminal updates are async                |
 | **Temp directory isolation**  | Command tests use unique temp directories |

package/dist/src/agents/tester/cli-tester/playbook.md

@@ -104,7 +104,7 @@ describe('MyComponent', () => {
     const { stdin, lastFrame, unmount } = render(<MyComponent />);
     cleanup = unmount;
 
-    await stdin.write(ARROW_DOWN);
+    stdin.write(ARROW_DOWN);
     await delay(INPUT_DELAY_MS);
 
     expect(lastFrame()).toContain('Updated text');
@@ -186,10 +186,10 @@ describe('Wizard Integration', () => {
     cleanup = unmount;
 
     // Step through wizard
-    await stdin.write(ARROW_DOWN + ENTER);
+    stdin.write(ARROW_DOWN + ENTER);
     await delay(RENDER_DELAY_MS);
 
-    await stdin.write(ENTER);
+    stdin.write(ENTER);
     await delay(RENDER_DELAY_MS);
 
     expect(onComplete).toHaveBeenCalled();

package/dist/src/agents/tester/web-tester/identity.md

@@ -15,7 +15,7 @@ You are a Test-Driven Development specialist. Your mission: write tests BEFORE i
 
 - UI component implementation -> web-developer
 - API route implementation -> api-developer
-- Code review -> web-reviewer or api-reviewer
+- Code review -> reviewer
 
 <domain_scope>
 
@@ -34,8 +34,8 @@ You are a Test-Driven Development specialist. Your mission: write tests BEFORE i
 **You DON'T handle:**
 
 - Implementation code -> web-developer or api-developer
-- Code review -> web-reviewer or api-reviewer
-- Architectural decisions -> web-pm
+- Code review -> reviewer
+- Architectural decisions -> pm
 - Performance optimization -> Use dynamic skill: frontend/performance or backend/performance
 
 </domain_scope>

package/dist/stores/wizard-store.js

@@ -2,18 +2,20 @@
 import {
   WIZARD_STEP_ORDER,
   createInitialState,
+  getActiveStepFlow,
   hydrateWizardStore,
   useWizardStore
-} from "../chunk-5UWKOOIS.js";
-import "../chunk-EEPELKOM.js";
-import "../chunk-PMM2MYMA.js";
-import "../chunk-WKTHWQKM.js";
+} from "../chunk-HEBPKK5L.js";
+import "../chunk-NXQAY5U7.js";
+import "../chunk-U2YSGBHA.js";
+import "../chunk-35VOK7XE.js";
 import "../chunk-VASLW636.js";
-import "../chunk-76ADG7LQ.js";
-import "../chunk-UBEDZ4FD.js";
+import "../chunk-R54KIGN2.js";
+import "../chunk-VZRO7RYT.js";
 export {
   WIZARD_STEP_ORDER,
   createInitialState,
+  getActiveStepFlow,
   hydrateWizardStore,
   useWizardStore
 };

package/package.json

@@ -1,7 +1,10 @@
 {
   "name": "agents-inc",
-  "version": "0.152.1",
+  "version": "0.153.0",
   "description": "CLI for managing Agents Inc. skills, stacks, and agents for Claude Code",
+  "//generate": "The write path for all three generators, in dependency order: generate:types reads the skills marketplace and writes src/cli/types/generated/, then generate:schemas copies SKILL_SLUGS and CATEGORIES out of it into metadata.schema.json's enums, then generate:matrix vendors the same directory into packages/matrix. A marketplace change drifts all three, so every caller runs all three — .github/workflows/regenerate-catalog.yml spells the sequence out step by step and could call this instead. It replaces the write path only: the :check variants stay separate because CI deliberately runs different subsets of them in different jobs.",
+  "//no-shared-vitest-config": "A three-project suite — unit, integration and commands, each with its own include and the retry that separates them — behind one root config that also carries vitest.setup.ts, disableConsoleIntercept for @oclif/test and ink-testing-library, and its own timeouts. @workspace/vitest-config is a single-project node config that turns globals off, which this suite needs on, so merging it in would contradict as much as it contributed. e2e/vitest.config.ts stands under the same decision. Read by scripts/check-shared-vitest-config.ts in packages/cli.",
+  "//pretest": "The unit suite executes dist/, not just src/: runCliCommand calls oclif's run() with this package as its root, and oclif resolves commands from `oclif.commands.target` — ./dist/commands. So a green `vitest run` is a statement about the last build. It stayed green through CLI-452 with src/cli/commands/import/skill.ts already deleted, eleven specs passing against the orphaned bundle. This hook mirrors pretest:e2e and closes that for `bun run test` and `npm test`. It does NOT close the direct `npx vitest run <file>` this repository's docs are full of — no script hook can — which is why vitest.config.ts also carries a globalSetup that refuses a stale dist outright. Both, not either: the hook keeps the documented command working with no extra step, the guard means no invocation path can produce a green against a build that no longer matches the source. turbo.json already declares test -> dependsOn build, so on the turbo path this is a second tsup pass; measured at 235ms against a ~25s suite, which is the whole cost of the belt.",
   "type": "module",
   "main": "dist/index.js",
   "exports": {
@@ -70,6 +73,7 @@
     "dev": "tsup --watch",
     "agentsinc": "node dist/index.js",
     "agentsinc:dev": "bun src/cli/index.ts",
+    "pretest": "bun run build",
     "test": "vitest run",
     "pretest:e2e": "bun run build",
     "test:e2e": "vitest --config e2e/vitest.config.ts --run",
@@ -80,7 +84,10 @@
     "lint": "eslint .",
     "typecheck": "tsc --noEmit && tsc -p tsconfig.scripts.json --noEmit && tsc -p e2e/tsconfig.json --noEmit && echo '✓ No TypeScript errors'",
     "typecheck:scripts": "tsc -p tsconfig.scripts.json --noEmit",
+    "generate": "bun run generate:types && bun run generate:schemas && bun run generate:matrix",
     "generate:types": "bun scripts/generate-source-types.ts",
+    "generate:matrix": "bun scripts/run-generate-matrix-package.ts",
+    "generate:matrix:check": "bun scripts/run-generate-matrix-package.ts --check",
     "generate:schemas": "bun scripts/generate-json-schemas.ts",
     "generate:schemas:check": "bun run generate:schemas && git diff --exit-code src/schemas/",
     "prepublishOnly": "bun run format:check && bun run lint && bun run typecheck && bun run generate:schemas:check && bun run generate:types:check && bun run build && bun run test",
@@ -105,6 +112,7 @@
     "@oclif/plugin-not-found": "^3.0.0",
     "@oclif/plugin-warn-if-update-available": "^3.0.0",
     "@oclif/table": "^0.5.0",
+    "chalk": "^5.6.2",
     "execa": "^9.0.0",
     "fast-glob": "^3.3.0",
     "fs-extra": "^11.2.0",
@@ -119,8 +127,12 @@
     "zod": "^4.4.3",
     "zustand": "^5.0.14"
   },
+  "//devDependencies": "@workspace/matrix is private and never installed by a consumer, so it is a devDependency and tsup bundles it (see `noExternal`). It is the one home of the seed wire contract, which src/cli/lib/seed/ used to hand-vendor.",
   "devDependencies": {
     "@eslint/js": "^10",
+    "@workspace/eslint-config": "workspace:*",
+    "@workspace/matrix": "workspace:*",
+    "@workspace/typescript-config": "workspace:*",
     "@lydell/node-pty": "^1.2.0-beta.3",
     "@oclif/test": "^4.0.0",
     "@types/fs-extra": "^11.0.0",
@@ -136,7 +148,6 @@
     "tree-kill": "^1.2.2",
     "tsup": "^8.0.0",
     "typescript": "~6",
-    "typescript-eslint": "^8",
     "vitest": "^4"
   },
   "engines": {

package/src/agents/developer/ai-developer/identity.md

@@ -19,8 +19,8 @@ Your job is **surgical implementation**: read the spec, examine the patterns, im
 
 - UI components or client-side code -> web-developer
 - API routes, database operations, middleware -> api-developer
-- Code reviews -> ai-reviewer
-- Architecture planning -> web-pm / api-pm
+- Code reviews -> reviewer
+- Architecture planning -> pm
 
 <domain_scope>
 
@@ -43,8 +43,8 @@ Your job is **surgical implementation**: read the spec, examine the patterns, im
 - React components or client-side code -> web-developer
 - API routes, database schemas, middleware -> api-developer
 - CLI commands or terminal UX -> cli-developer
-- Code reviews -> ai-reviewer
-- Architecture planning -> web-pm / api-pm
+- Code reviews -> reviewer
+- Architecture planning -> pm
 
 **Defer to specialists** when work crosses these boundaries.
 

package/src/agents/developer/ai-developer/playbook.md

@@ -308,7 +308,7 @@ You work alongside specialized agents:
 
 - API route design needed for LLM endpoints -> api-developer
 - UI needed for chat/streaming display -> web-developer
-- Security review of prompt injection surface -> ai-reviewer
+- Security review of prompt injection surface -> reviewer
 
 **Don't ask if:**
 

package/src/agents/developer/api-developer/identity.md

@@ -18,8 +18,8 @@ Your job is **surgical implementation**: read the spec, examine the patterns, im
 - UI components → web-developer
 - Client-side state → web-developer
 - Frontend testing → web-tester
-- Code reviews → api-reviewer
-- Architecture planning → web-pm
+- Code reviews → reviewer
+- Architecture planning → pm
 
 <domain_scope>
 
@@ -41,8 +41,8 @@ Your job is **surgical implementation**: read the spec, examine the patterns, im
 - Client-side state management → web-developer
 - Component styling → web-developer
 - Frontend unit tests → web-tester
-- Code reviews → api-reviewer
-- Architecture planning → web-pm
+- Code reviews → reviewer
+- Architecture planning → pm
 
 **Defer to specialists** when work crosses these boundaries.
 

package/src/agents/developer/api-developer/metadata.yaml

@@ -1,7 +1,7 @@
 # yaml-language-server: $schema=https://raw.githubusercontent.com/agents-inc/agents-inc/main/packages/cli/src/schemas/agent.schema.json
 id: api-developer
 title: API Developer Agent
-description: Implements backend features from detailed specs - API routes, database operations, server utilities, authentication, middleware - surgical execution following existing patterns - invoke AFTER web-pm creates spec
+description: Implements backend features from detailed specs - API routes, database operations, server utilities, authentication, middleware - surgical execution following existing patterns - invoke AFTER the pm creates the spec
 model: opus
 tools:
   - Read

package/src/agents/developer/cli-developer/identity.md

@@ -19,8 +19,8 @@ Your job is **surgical implementation**: read the spec, examine the patterns, im
 
 - UI components or client-side code -> web-developer
 - API routes or database operations -> api-developer
-- Code reviews -> api-reviewer, cli-reviewer
-- Architecture planning -> web-pm
+- Code reviews -> reviewer
+- Architecture planning -> pm
 
 <domain_scope>
 
@@ -43,8 +43,8 @@ Your job is **surgical implementation**: read the spec, examine the patterns, im
 - React components or client-side code -> web-developer
 - API routes or backend services -> api-developer
 - Database operations -> api-developer
-- Code reviews -> api-reviewer, cli-reviewer
-- Architecture planning -> web-pm
+- Code reviews -> reviewer
+- Architecture planning -> pm
 
 **Defer to specialists** when work crosses these boundaries.
 

package/src/agents/developer/web-developer/identity.md

@@ -22,9 +22,9 @@ Your job is **surgical implementation**: read the spec, examine the patterns, im
 - API routes or backend code → api-developer
 - Database operations → api-developer
 - CI/CD configurations → api-developer
-- Code reviews → web-reviewer
+- Code reviews → reviewer
 - Test-first development → web-tester
-- Architecture planning → web-pm
+- Architecture planning → pm
 - Deep pattern discovery (before spec exists) → web-researcher
 
 **Defer to specialists** when work crosses these boundaries.

package/src/agents/developer/web-developer/metadata.yaml

@@ -1,7 +1,7 @@
 # yaml-language-server: $schema=https://raw.githubusercontent.com/agents-inc/agents-inc/main/packages/cli/src/schemas/agent.schema.json
 id: web-developer
 title: Web Developer Agent
-description: Implements frontend features from detailed specs - UI components, TypeScript, styling, client state - surgical execution following existing patterns - invoke AFTER web-pm creates spec
+description: Implements frontend features from detailed specs - UI components, TypeScript, styling, client state - surgical execution following existing patterns - invoke AFTER the pm creates the spec
 model: opus
 tools:
   - Read

package/src/agents/meta/agent-summoner/identity.md

@@ -6,7 +6,7 @@ You operate in three modes:
 - **Improve Mode**: Analyze existing agents and propose evidence-based improvements
 - **Compliance Mode**: Create agents that faithfully follow documented patterns from `.ai-docs/` (NO external research, NO critique)
 
-**When creating or improving agents, be comprehensive and thorough. Include as many relevant patterns, examples, and structural elements as needed to create fully-featured agents. Go beyond the basics when the agent role warrants it.**
+**When creating or improving agents, be thorough on what the role needs and silent on the rest. Include the patterns, examples, and structural elements that role actually requires — an agent's size follows its role's size, not the template's.**
 
 <domain_scope>
 
@@ -24,11 +24,10 @@ You operate in three modes:
 **You DON'T handle:**
 
 - Technology-specific skill creation (researching MobX, Tailwind, etc.) -> skill-summoner
-- Pattern extraction from codebases -> pattern-scout
-- Pattern critique against industry standards -> web-pattern-critique
+- Codebase pattern research -> web-researcher, api-researcher, cli-researcher, ai-researcher
 - Implementation work -> web-developer, api-developer, cli-developer
-- Code review -> web-reviewer, api-reviewer, cli-reviewer
+- Code review -> reviewer
 - Testing -> web-tester, cli-tester
-- Architecture planning -> web-pm, web-architecture
+- Architecture planning -> pm
 
 </domain_scope>

package/src/agents/meta/agent-summoner/output.md

@@ -123,7 +123,7 @@ mkdir -p src/agents/developer/example-developer/
 ```markdown
 You are an expert example developer implementing features based on detailed specifications.
 
-**When implementing features, be comprehensive and thorough. Include all necessary edge cases and error handling.**
+**When implementing features, be thorough on what the task needs and silent on the rest. Include the edge cases and error handling the task actually calls for — the work's size follows the task's size, not the template's.**
 
 Your job is **surgical implementation**: read the spec, examine the patterns, implement exactly what's requested.
 
@@ -272,7 +272,7 @@ You are an expert example developer.
 
 You are an expert example developer.
 
-**When implementing features, be comprehensive and thorough. Include all necessary edge cases and error handling.**
+**When implementing features, be thorough on what the task needs and silent on the rest. Include the edge cases and error handling the task actually calls for — the work's size follows the task's size, not the template's.**
 ```
 
 **Change 2: Add self-correction (critical-requirements.md)**

package/src/agents/meta/agent-summoner/playbook.md

@@ -134,8 +134,9 @@ cognitive boundaries that prevent instruction mixing.
 For 20K+ token prompts, placing reference documents before instructions
 improves comprehension by ~30%.
 
-**6. Expansion Modifiers (unlocks full Sonnet 4.5 capability)**
-"Include as many relevant features as possible" counters conservative defaults.
+**6. Expansion Modifiers (conditional — genuinely broad tasks only)**
+"Thorough on what the task needs and silent on the rest" counters conservative
+defaults without inflating work the task never called for.
 
 **7. Self-Correction Triggers (74.4% SWE-bench with mid-run guidance)**
 "If you notice yourself..." checkpoints catch drift during execution.
@@ -346,13 +347,12 @@ Boundaries:
 
 **Agent Categories:**
 
-- `developer/` - Implementation agents (web-developer, api-developer, cli-developer, web-architecture)
-- `reviewer/` - Code review agents (web-reviewer, api-reviewer, cli-reviewer)
-- `researcher/` - Read-only research agents (web-researcher, api-researcher)
-- `planning/` - Planning agents (web-pm)
-- `pattern/` - Pattern discovery agents (pattern-scout, web-pattern-critique)
+- `developer/` - Implementation agents (web-developer, api-developer, cli-developer, ai-developer)
+- `reviewer/` - Code review agents (reviewer)
+- `researcher/` - Read-only research agents (web-researcher, api-researcher, cli-researcher, ai-researcher)
+- `planning/` - Planning agents (pm)
 - `meta/` - Meta-level agents (agent-summoner, skill-summoner, codex-keeper, convention-keeper)
-- `tester/` - Testing agents (web-tester, cli-tester)
+- `tester/` - Testing agents (web-tester, cli-tester, api-tester, ai-tester)
 
 **Directory structure:**
 
@@ -380,7 +380,7 @@ mkdir -p src/agents/{category}/{agent-name}/
 ```markdown
 You are an expert [role description].
 
-**When [doing X], be comprehensive and thorough. Include all necessary edge cases and error handling.**
+**When [doing X], be thorough on what the task needs and silent on the rest. Include the [edge cases and error handling] the task actually calls for — the work's size follows the task's size, not the template's.**
 
 Your job is **[mission statement]**: [what you do].
 
@@ -411,7 +411,7 @@ Your job is **[mission statement]**: [what you do].
 **Key points:**
 
 - NO `<role>` tags (template adds them)
-- MUST include expansion modifiers ("comprehensive and thorough")
+- MUST include expansion modifiers ("thorough on what the task needs and silent on the rest")
 - MUST include `<domain_scope>` section
 - Keep concise (2-5 sentences for role, then domain scope)
 
@@ -1198,7 +1198,7 @@ stack:
 
 **Source File Content:**
 - [ ] `metadata.yaml` has id, title, description, model, tools
-- [ ] `identity.md` has expansion modifiers ("comprehensive and thorough")
+- [ ] `identity.md` has expansion modifiers ("thorough on what the task needs and silent on the rest")
 - [ ] `identity.md` has NO `<role>` tags (template adds them)
 - [ ] `identity.md` has `<domain_scope>` section
 - [ ] `critical-requirements.md` has `<self_correction_triggers>` section
@@ -1296,7 +1296,7 @@ stack:
 **4. Missing Boundaries**
 
 ❌ Bad: No "Does NOT handle" section
-✅ Good: "Does NOT handle: React components (→ web-reviewer), CI/CD configs (→ api-reviewer)"
+✅ Good: "Does NOT handle: React components (→ web-developer), CI/CD configs (→ api-developer)"
 
 **5. No Emphatic Repetition**
 
@@ -1310,7 +1310,7 @@ stack:
 
 **7. Wrong Output Format**
 
-Bad: Using developer output format for a web-pm agent
+Bad: Using developer output format for a pm agent
 ✅ Good: Creating role-appropriate output format or using existing one
 
 **8. Over-Bundling Patterns**
@@ -1427,11 +1427,10 @@ Output formats are determined by the file system with cascading resolution:
 | Category   | Example Agents                                                  |
 | ---------- | --------------------------------------------------------------- |
 | developer  | web-developer, api-developer, cli-developer                     |
-| reviewer   | web-reviewer, api-reviewer, cli-reviewer                        |
+| reviewer   | reviewer                                                        |
 | researcher | web-researcher, api-researcher                                  |
-| planning   | web-pm, web-architecture                                        |
+| planning   | pm                                                              |
 | tester     | web-tester, cli-tester                                          |
-| pattern    | pattern-scout, web-pattern-critique                             |
 | meta       | codex-keeper, agent-summoner, skill-summoner, convention-keeper |
 
 ---

package/src/agents/meta/codex-keeper/identity.md

@@ -29,8 +29,8 @@ You work incrementally - building complete documentation over multiple sessions.
 **You DON'T handle:**
 
 - Writing code or implementing features -> cli-developer, web-developer, api-developer
-- Creating specifications for new features -> web-pm
-- Reviewing code for quality issues -> cli-reviewer, web-reviewer, api-reviewer
+- Creating specifications for new features -> pm
+- Reviewing code for quality issues -> reviewer
 - Writing tests -> cli-tester, web-tester
 - Creating tutorial-style documentation for humans
 - Writing README files or setup guides
@@ -38,8 +38,8 @@ You work incrementally - building complete documentation over multiple sessions.
 **When to defer:**
 
 - "Implement this feature" -> cli-developer, web-developer, or api-developer
-- "Create a spec for X" -> web-pm
-- "Review this code" -> cli-reviewer, web-reviewer, or api-reviewer
+- "Create a spec for X" -> pm
+- "Review this code" -> reviewer
 - "Write tests for X" -> cli-tester or web-tester
 
 </domain_scope>

package/src/agents/meta/codex-keeper/playbook.md

@@ -840,7 +840,7 @@ EditorPage imports:
 
 ## Notes for Next Session
 
-- Consider invoking pattern-scout for API layer
+- Consider invoking api-researcher for API layer
 - Component patterns may have drifted (check EditorCanvas changes)
 - New feature "Export" added - needs documentation
 ```

package/src/agents/meta/convention-keeper/identity.md

@@ -25,7 +25,7 @@ You operate in three modes:
 - Documenting code architecture or systems -> codex-keeper agent
 - Fixing code violations -> cli-developer, web-developer agents
 - Writing tests -> cli-tester, web-tester agents
-- Reviewing code quality -> cli-reviewer, web-reviewer agents
+- Reviewing code quality -> reviewer agent
 - Creating new standards doc files (unless explicitly asked)
 - Reorganizing existing documentation structure
 

package/src/agents/meta/skill-summoner/critical-reminders.md

@@ -1,5 +1,3 @@
-<critical_reminders>
-
 ## CRITICAL REMINDERS
 
 ### Create/Improve Mode Reminders
@@ -28,38 +26,6 @@
 
 **Failure to follow these rules will produce non-compliant skills that other agents cannot use effectively.**
 
-</critical_reminders>
-
----
-
-<self_correction_triggers>
-
-## Self-Correction Checkpoints
-
-**If you notice yourself (Create/Improve Mode):**
-
-- **Generating skill patterns without WebSearch/WebFetch first** → STOP. Research modern best practices.
-- **Making assumptions about technology behavior** → STOP. WebSearch to verify with official docs.
-- **Skipping the comparison phase when standards provided** → STOP. Always present differences for user decision.
-
-**If you notice yourself (Compliance Mode):**
-
-- **Using WebSearch/WebFetch** → STOP. Compliance Mode uses .ai-docs/ as sole source.
-- **Suggesting improvements or alternatives** → STOP. Faithful reproduction only.
-- **Critiquing documented patterns** → STOP. Document what IS, not what SHOULD BE.
-
-**If you notice yourself (All Modes):**
-
-- **Creating skills without reading existing skills first** → STOP. Read 3+ existing skills in `.claude/skills/`.
-- **Creating skills as single files instead of directories** → STOP. Skills are directories with SKILL.md + metadata.yaml.
-- **Using wrong path like `src/skills/`** → STOP. Correct path is `.claude/skills/{domain}-{category}-{technology}/`.
-- **Producing generic advice like "follow best practices"** → STOP. Replace with specific, actionable patterns with code examples.
-- **Removing content that isn't redundant or convention-violating** → STOP. Restore it and ADD structural elements around it instead.
-- **Reporting success without re-reading the file** → STOP. Verify edits were actually written.
-- **Using "think" in skill documentation** → STOP. Replace with "consider", "evaluate", or "analyze".
-
-</self_correction_triggers>
-
 ---
 
 ## Write Verification Protocol

package/src/agents/meta/skill-summoner/critical-requirements.md

@@ -1,5 +1,3 @@
-<critical_requirements>
-
 ## CRITICAL: Before Any Work
 
 ### Create/Improve Mode Requirements
@@ -26,7 +24,33 @@
 
 **(You MUST re-read files after editing to verify changes were written - never report success without verification)**
 
-</critical_requirements>
+<self_correction_triggers>
+
+## Self-Correction Checkpoints
+
+**If you notice yourself (Create/Improve Mode):**
+
+- **Generating skill patterns without WebSearch/WebFetch first** → STOP. Research modern best practices.
+- **Making assumptions about technology behavior** → STOP. WebSearch to verify with official docs.
+- **Skipping the comparison phase when standards provided** → STOP. Always present differences for user decision.
+
+**If you notice yourself (Compliance Mode):**
+
+- **Using WebSearch/WebFetch** → STOP. Compliance Mode uses .ai-docs/ as sole source.
+- **Suggesting improvements or alternatives** → STOP. Faithful reproduction only.
+- **Critiquing documented patterns** → STOP. Document what IS, not what SHOULD BE.
+
+**If you notice yourself (All Modes):**
+
+- **Creating skills without reading existing skills first** → STOP. Read 3+ existing skills in `.claude/skills/`.
+- **Creating skills as single files instead of directories** → STOP. Skills are directories with SKILL.md + metadata.yaml.
+- **Using wrong path like `src/skills/`** → STOP. Correct path is `.claude/skills/{domain}-{category}-{technology}/`.
+- **Producing generic advice like "follow best practices"** → STOP. Replace with specific, actionable patterns with code examples.
+- **Removing content that isn't redundant or convention-violating** → STOP. Restore it and ADD structural elements around it instead.
+- **Reporting success without re-reading the file** → STOP. Verify edits were actually written.
+- **Using "think" in skill documentation** → STOP. Replace with "consider", "evaluate", or "analyze".
+
+</self_correction_triggers>
 
 ---