@softspark/ai-toolkit 1.3.7 → 1.3.9

package/CHANGELOG.md

@@ -7,6 +7,29 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 
 ---
 
+## v1.3.9 — Single Source of Truth for Counts (2026-04-07)
+
+### Changed
+- **Counts policy**: Hardcoded skill/agent/hook/test counts removed from all secondary docs. Only README.md, manifest.json, and package.json contain counts. Rule: `kb/best-practices/no-hardcoded-counts.md`.
+- **47 new tests** (327 → 374): MCP manager, language auto-detect, install state, version check, new hooks, orphan cleanup.
+
+### Fixed
+- manifest.json version synced (was 1.0.0)
+- plugin.json version synced (was 1.2.1)
+- agents-catalog.md version aligned
+- ARCHITECTURE.md hook event multipliers corrected
+- Generator scripts no longer embed counts
+
+---
+
+## v1.3.8 — Language Rules as References (2026-04-07)
+
+### Changed
+- **Language rules injection**: Instead of inlining full rule content (~705 lines), `install --local` now injects lightweight reference pointers (~12 lines) with absolute paths to rule files. Claude reads them on demand via Read tool, keeping CLAUDE.md compact.
+- **plugin.json**: Version synced from stale 1.2.1 to 1.3.8.
+
+---
+
 ## v1.3.7 — Update Notifications (2026-04-07)
 
 ### Added

package/README.md

@@ -6,7 +6,7 @@
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![Skills](https://img.shields.io/badge/skills-90-brightgreen)](app/skills/)
 [![Agents](https://img.shields.io/badge/agents-44-blue)](app/agents/)
-[![Tests](https://img.shields.io/badge/tests-327%20passing-success)](tests/)
+[![Tests](https://img.shields.io/badge/tests-374%20passing-success)](tests/)
 
 ---
 

package/app/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "ai-toolkit",
-  "description": "Professional-grade Claude Code toolkit: 90 skills, 44 agents, persona presets, skill security auditor, expanded lifecycle hooks, experimental opt-in plugin packs, benchmark harvesting, and multi-tool support.",
-  "version": "1.2.1",
+  "description": "Professional-grade Claude Code toolkit with persona presets, skill security auditor, expanded lifecycle hooks, experimental opt-in plugin packs, benchmark harvesting, and multi-tool support.",
+  "version": "1.3.8",
   "author": {
     "name": "SoftSpark",
     "url": "https://github.com/softspark"

package/app/ARCHITECTURE.md

@@ -6,13 +6,13 @@ Universal multi-agent system for software development. Works across all reposito
 
 | Component | Count |
 |-----------|-------|
-| Agents | 44 |
-| Skills | 90 |
-| Hooks | 12 events / 21 entries (SessionStart, Notification, PreToolUse ×2, UserPromptSubmit ×2, PostToolUse, Stop ×2, TaskCompleted, TeammateIdle, SubagentStart, SubagentStop, PreCompact, SessionEnd) |
+| Agents | See agents catalog |
+| Skills | See skills catalog |
+| Hooks | 12 events / 21 entries (SessionStart ×3, Notification ×1, PreToolUse ×4, UserPromptSubmit ×2, PostToolUse ×2, Stop ×2, TaskCompleted ×1, TeammateIdle ×1, SubagentStart ×1, SubagentStop ×1, PreCompact ×2, SessionEnd ×1) |
 
 ---
 
-## Agents (44)
+## Agents
 
 ### Orchestration & Planning (4)
 | Agent | Model | Purpose |
@@ -100,7 +100,7 @@ Universal multi-agent system for software development. Works across all reposito
 
 ---
 
-## Skills (90)
+## Skills
 
 ### Task Skills (28)
 | Skill | Slash Command | Purpose |
@@ -255,9 +255,9 @@ Phase 2: IMPLEMENTATION
 ```
 .claude/
 ├── ARCHITECTURE.md      # This file
-├── agents/              # Agent definitions (44)
+├── agents/              # Agent definitions
 ├── hooks.json           # Quality gate hooks (multi-language)
-├── skills/              # All skills: task, hybrid, knowledge (90)
+├── skills/              # All skills: task, hybrid, knowledge
 ├── output-styles/       # System prompt output style overrides (e.g. golden-rules)
 ├── constitution.md      # Immutable safety rules (5 articles)
 └── settings.local.json  # Local settings + Agent Teams config

package/app/rules/claude-toolkit-rules.md

@@ -1,6 +1,6 @@
 # Claude Toolkit
 
-Shared AI development toolkit — 90 skills, 44 agents, lifecycle hooks, safety constitution.
+Shared AI development toolkit — lifecycle hooks, safety constitution, multi-platform support.
 
 ## Skill Tiers
 

package/kb/best-practices/no-hardcoded-counts.md

@@ -0,0 +1,41 @@
+---
+title: "No Hardcoded Counts in Secondary Docs"
+category: best-practices
+service: ai-toolkit
+tags: [counts, documentation, maintenance, skills, agents, hooks, tests]
+created: "2026-04-07"
+last_updated: "2026-04-07"
+description: "Counts (skills, agents, hooks, tests) should only appear in README.md and manifest.json. All other docs must NOT contain hardcoded numbers to avoid drift."
+---
+
+# No Hardcoded Counts in Secondary Docs
+
+## Rule
+
+Hardcoded counts (skills, agents, hooks, tests, plugins) are allowed ONLY in:
+- **README.md** — badges, "What You Get" table, comparison table
+- **manifest.json** — module descriptions
+- **package.json** — description field
+
+All other files (CLAUDE.md, ARCHITECTURE.md, KB docs, plugin.json, llms.txt, AGENTS.md, copilot-instructions, rules, GEMINI.md) must NOT contain hardcoded counts like "90 skills" or "44 agents".
+
+## Why
+
+Every time a skill, agent, or hook is added/removed, dozens of files need updating. This causes constant drift and stale counts that erode trust. Consolidating to 2-3 files makes maintenance tractable.
+
+## How to Apply
+
+- In secondary docs, use relative language: "all agents", "the full skill set", "available hooks"
+- If a doc MUST reference scale, use: "see README.md for current counts"
+- `validate.py` checks counts only in README.md badges — that's sufficient
+- When adding skills/agents/hooks, update ONLY: README.md badges + manifest.json descriptions
+
+## Anti-Pattern
+
+```markdown
+# BAD — hardcoded count in ARCHITECTURE.md
+Shared AI development toolkit — 90 skills, 44 agents
+
+# GOOD — no count
+Shared AI development toolkit with multi-platform support
+```

package/kb/reference/agents-catalog.md

@@ -3,13 +3,13 @@ title: "AI Toolkit - Agents Catalog"
 category: reference
 service: ai-toolkit
 tags: [agents, catalog, roles, ai-development]
-version: "2.0.0"
+version: "1.3.8"
 created: "2026-03-23"
 last_updated: "2026-03-25"
-description: "Complete catalog of 44 specialized agents with roles, models, and use cases."
+description: "Complete catalog of specialized agents with roles, models, and use cases."
 ---
 
-# Agents Catalog (44 agents)
+# Agents Catalog
 
 ## By Category
 

package/kb/reference/architecture-overview.md

@@ -13,7 +13,7 @@ description: "Architecture of ai-toolkit: directory layout, global install model
 
 ## Purpose
 
-Shared, project-agnostic AI development toolkit for Claude Code (and compatible assistants like Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, and Augment). Provides 44 specialized agents, 90 skills (slash commands + knowledge), expanded lifecycle hooks, persona presets, and experimental opt-in plugin packs that teams can adopt separately from the default global install.
+Shared, project-agnostic AI development toolkit for Claude Code (and compatible assistants like Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, and Augment). Provides specialized agents, skills (slash commands + knowledge), expanded lifecycle hooks, persona presets, and experimental opt-in plugin packs that teams can adopt separately from the default global install.
 
 ## Design Principles
 
@@ -30,8 +30,8 @@ ai-toolkit/
   bin/
     ai-toolkit.js        # CLI entry point (install, init, add-rule, ...)
   app/                       # All toolkit components
-    agents/                  # 44 agent definitions (.md + YAML frontmatter)
-    skills/                  # 90 skills: task, hybrid, knowledge
+    agents/                  # Agent definitions (.md + YAML frontmatter)
+    skills/                  # skills: task, hybrid, knowledge
     rules/                   # Rules auto-injected into ~/.claude/CLAUDE.md
     hooks/                   # Hook scripts (copied to ~/.ai-toolkit/hooks/)
     hooks.json               # Hook definitions (merged into ~/.claude/settings.json)

package/kb/reference/commands-catalog.md

@@ -13,7 +13,7 @@ description: "DEPRECATED: All slash commands are implemented as skills. See skil
 
 All slash commands have been migrated to skills.
 
-See **[Skills Catalog](skills-catalog.md)** for the complete list of 90 skills, including:
+See **[Skills Catalog](skills-catalog.md)** for the complete list of skills, including:
 - **28 Task Skills** — formerly standalone commands and creator workflows (e.g., `/commit`, `/test`, `/deploy`, `/hook-creator`, `/plugin-creator`)
 - **30 Hybrid Skills** — slash commands that also provide agent knowledge (e.g., `/review`, `/debug`, `/plan`, `/tdd`, `/write-a-prd`, `/council`, `/introspect`)
 - **32 Knowledge Skills** — domain patterns auto-loaded by agents (e.g., `brand-voice`, `clean-code`, `testing-patterns`)

package/kb/reference/competitive-features-implementation.md

@@ -35,7 +35,7 @@ Strengthen ai-toolkit's competitive position by implementing 10 features from co
 **Key design principle:** ai-toolkit is a **generic toolkit** — it does NOT know about rag-mcp or any specific consumer. Consumers (like rag-mcp) use ai-toolkit's public API (`inject-rule`, `inject-hook`, `merge-hooks`) to add their own rules and hooks.
 
 **State before plan:** 88 skills, 47 agents, 14 hooks, 9 editor integrations
-**State after plan:** 90 skills, 44 agents, 21 hooks, 70 language rules, 25 MCP templates, extension API
+**State after plan:** See manifest.json for current counts. Target: skills, agents, hooks, 70 language rules, 25 MCP templates, extension API
 
 ---
 
@@ -384,7 +384,7 @@ All entries are tagged with "_source": "<source-name>" for idempotent updates.
       "required": true
     },
     "agents": {
-      "description": "44 specialized agents",
+      "description": "Specialized agents",
       "files": ["app/agents/*.md"],
       "required": false,
       "default": true

package/kb/reference/extension-api.md

@@ -3,7 +3,7 @@ title: "Extension API Reference"
 category: reference
 service: ai-toolkit
 tags: [extension-api, inject-rule, inject-hook, mcp-templates, integration]
-version: "1.3.0"
+version: "1.3.8"
 created: "2026-04-07"
 last_updated: "2026-04-07"
 description: "Reference for ai-toolkit's extension API: inject-rule, inject-hook, remove-rule, remove-hook, and mcp template management."

package/kb/reference/manifest-install.md

@@ -24,8 +24,8 @@ Modules are defined in `manifest.json` at the repository root. There are 17 modu
 | Module | Description | In Profile |
 |--------|-------------|-----------|
 | `core` | Core hooks and essential skills | minimal, standard, strict, full |
-| `agents` | 44 specialized agents | standard, strict, full |
-| `skills` | 90 skills (task, hybrid, knowledge) | standard, strict, full |
+| `agents` | Specialized agents | standard, strict, full |
+| `skills` | All skills (task, hybrid, knowledge) | standard, strict, full |
 | `rules-common` | Common coding rules (5 files) | standard, strict, full |
 | `rules-typescript` | TypeScript-specific rules (5 files) | auto-detect |
 | `rules-python` | Python-specific rules (5 files) | auto-detect |

package/kb/reference/skills-catalog.md

@@ -3,13 +3,13 @@ title: "AI Toolkit - Skills Catalog"
 category: reference
 service: ai-toolkit
 tags: [skills, domain-knowledge, catalog, task-skills, hybrid-skills]
-version: "1.3.3"
+version: "1.3.8"
 created: "2026-03-23"
 last_updated: "2026-04-07"
-description: "Complete catalog of 90 skills: 28 task, 30 hybrid, 32 knowledge. Includes effort levels, skill-scoped hooks, executable scripts, security auditor, and persona presets."
+description: "Complete skills catalog with task, hybrid, and knowledge skills. Includes effort levels, skill-scoped hooks, executable scripts, security auditor, and persona presets."
 ---
 
-# Skills Catalog (90 skills)
+# Skills Catalog
 
 All functionality is unified under skills. Task and hybrid skills are user-invocable as slash commands. Knowledge skills provide domain patterns auto-loaded by agents.
 

package/llms-full.txt

@@ -1,6 +1,6 @@
 # ai-toolkit
 
-> Professional-grade Claude Code toolkit: 90 skills, 44 agents, machine-enforced constitution, quality hooks.
+> Professional-grade Claude Code toolkit: skills, agents, machine-enforced constitution, quality hooks.
 
 ## Documentation
 
@@ -12,9 +12,10 @@
 ## Knowledge Base
 
 - [Best Practices](kb/best-practices/README.md)
+- [No Hardcoded Counts in Secondary Docs](kb/best-practices/no-hardcoded-counts.md)
 - [How-To Guides](kb/howto/README.md)
 - [SOP: Claude Toolkit Maintenance](kb/procedures/maintenance-sop.md)
-- [Agents Catalog (44 agents)](kb/reference/agents-catalog.md)
+- [Agents Catalog](kb/reference/agents-catalog.md)
 - [Anti-Pattern Registry Format](kb/reference/anti-pattern-registry-format.md)
 - [AI Toolkit Architecture](kb/reference/architecture-overview.md)
 - [Config Benchmark](kb/reference/benchmark-config.md)
@@ -37,7 +38,7 @@
 - [Plugin Pack Conventions](kb/reference/plugin-pack-conventions.md)
 - [Quick Wins Implementation Summary](kb/reference/quick-wins-implementation-summary.md)
 - [Skill Templates](kb/reference/skill-templates.md)
-- [Skills Catalog (90 skills)](kb/reference/skills-catalog.md)
+- [Skills Catalog](kb/reference/skills-catalog.md)
 - [Skills Unification Model](kb/reference/skills-unification.md)
 - [Usage Statistics](kb/reference/stats.md)
 - [Config Sync](kb/reference/sync.md)
@@ -201,6 +202,52 @@ Guidelines and recommendations. Guides will be added here as they are created.
 
 ---
 
+## kb/best-practices/no-hardcoded-counts.md
+
+---
+title: "No Hardcoded Counts in Secondary Docs"
+category: best-practices
+service: ai-toolkit
+tags: [counts, documentation, maintenance, skills, agents, hooks, tests]
+created: "2026-04-07"
+last_updated: "2026-04-07"
+description: "Counts (skills, agents, hooks, tests) should only appear in README.md and manifest.json. All other docs must NOT contain hardcoded numbers to avoid drift."
+---
+
+# No Hardcoded Counts in Secondary Docs
+
+## Rule
+
+Hardcoded counts (skills, agents, hooks, tests, plugins) are allowed ONLY in:
+- **README.md** — badges, "What You Get" table, comparison table
+- **manifest.json** — module descriptions
+- **package.json** — description field
+
+All other files (CLAUDE.md, ARCHITECTURE.md, KB docs, plugin.json, llms.txt, AGENTS.md, copilot-instructions, rules, GEMINI.md) must NOT contain hardcoded counts like "90 skills" or "44 agents".
+
+## Why
+
+Every time a skill, agent, or hook is added/removed, dozens of files need updating. This causes constant drift and stale counts that erode trust. Consolidating to 2-3 files makes maintenance tractable.
+
+## How to Apply
+
+- In secondary docs, use relative language: "all agents", "the full skill set", "available hooks"
+- If a doc MUST reference scale, use: "see README.md for current counts"
+- `validate.py` checks counts only in README.md badges — that's sufficient
+- When adding skills/agents/hooks, update ONLY: README.md badges + manifest.json descriptions
+
+## Anti-Pattern
+
+```markdown
+# BAD — hardcoded count in ARCHITECTURE.md
+Shared AI development toolkit — 90 skills, 44 agents
+
+# GOOD — no count
+Shared AI development toolkit with multi-platform support
+```
+
+---
+
 ## kb/howto/README.md
 
 ---
@@ -535,13 +582,13 @@ title: "AI Toolkit - Agents Catalog"
 category: reference
 service: ai-toolkit
 tags: [agents, catalog, roles, ai-development]
-version: "2.0.0"
+version: "1.3.8"
 created: "2026-03-23"
 last_updated: "2026-03-25"
-description: "Complete catalog of 44 specialized agents with roles, models, and use cases."
+description: "Complete catalog of specialized agents with roles, models, and use cases."
 ---
 
-# Agents Catalog (44 agents)
+# Agents Catalog
 
 ## By Category
 
@@ -897,7 +944,7 @@ description: "Architecture of ai-toolkit: directory layout, global install model
 
 ## Purpose
 
-Shared, project-agnostic AI development toolkit for Claude Code (and compatible assistants like Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, and Augment). Provides 44 specialized agents, 90 skills (slash commands + knowledge), expanded lifecycle hooks, persona presets, and experimental opt-in plugin packs that teams can adopt separately from the default global install.
+Shared, project-agnostic AI development toolkit for Claude Code (and compatible assistants like Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, and Augment). Provides specialized agents, skills (slash commands + knowledge), expanded lifecycle hooks, persona presets, and experimental opt-in plugin packs that teams can adopt separately from the default global install.
 
 ## Design Principles
 
@@ -914,8 +961,8 @@ ai-toolkit/
   bin/
     ai-toolkit.js        # CLI entry point (install, init, add-rule, ...)
   app/                       # All toolkit components
-    agents/                  # 44 agent definitions (.md + YAML frontmatter)
-    skills/                  # 90 skills: task, hybrid, knowledge
+    agents/                  # Agent definitions (.md + YAML frontmatter)
+    skills/                  # skills: task, hybrid, knowledge
     rules/                   # Rules auto-injected into ~/.claude/CLAUDE.md
     hooks/                   # Hook scripts (copied to ~/.ai-toolkit/hooks/)
     hooks.json               # Hook definitions (merged into ~/.claude/settings.json)
@@ -1510,7 +1557,7 @@ description: "DEPRECATED: All slash commands are implemented as skills. See skil
 
 All slash commands have been migrated to skills.
 
-See **[Skills Catalog](skills-catalog.md)** for the complete list of 90 skills, including:
+See **[Skills Catalog](skills-catalog.md)** for the complete list of skills, including:
 - **28 Task Skills** — formerly standalone commands and creator workflows (e.g., `/commit`, `/test`, `/deploy`, `/hook-creator`, `/plugin-creator`)
 - **30 Hybrid Skills** — slash commands that also provide agent knowledge (e.g., `/review`, `/debug`, `/plan`, `/tdd`, `/write-a-prd`, `/council`, `/introspect`)
 - **32 Knowledge Skills** — domain patterns auto-loaded by agents (e.g., `brand-voice`, `clean-code`, `testing-patterns`)
@@ -1558,7 +1605,7 @@ Strengthen ai-toolkit's competitive position by implementing 10 features from co
 **Key design principle:** ai-toolkit is a **generic toolkit** — it does NOT know about rag-mcp or any specific consumer. Consumers (like rag-mcp) use ai-toolkit's public API (`inject-rule`, `inject-hook`, `merge-hooks`) to add their own rules and hooks.
 
 **State before plan:** 88 skills, 47 agents, 14 hooks, 9 editor integrations
-**State after plan:** 90 skills, 44 agents, 21 hooks, 70 language rules, 25 MCP templates, extension API
+**State after plan:** See manifest.json for current counts. Target: skills, agents, hooks, 70 language rules, 25 MCP templates, extension API
 
 ---
 
@@ -1907,7 +1954,7 @@ All entries are tagged with "_source": "<source-name>" for idempotent updates.
       "required": true
     },
     "agents": {
-      "description": "44 specialized agents",
+      "description": "Specialized agents",
       "files": ["app/agents/*.md"],
       "required": false,
       "default": true
@@ -2276,7 +2323,7 @@ title: "Extension API Reference"
 category: reference
 service: ai-toolkit
 tags: [extension-api, inject-rule, inject-hook, mcp-templates, integration]
-version: "1.3.0"
+version: "1.3.8"
 created: "2026-04-07"
 last_updated: "2026-04-07"
 description: "Reference for ai-toolkit's extension API: inject-rule, inject-hook, remove-rule, remove-hook, and mcp template management."
@@ -3454,8 +3501,8 @@ Modules are defined in `manifest.json` at the repository root. There are 17 modu
 | Module | Description | In Profile |
 |--------|-------------|-----------|
 | `core` | Core hooks and essential skills | minimal, standard, strict, full |
-| `agents` | 44 specialized agents | standard, strict, full |
-| `skills` | 90 skills (task, hybrid, knowledge) | standard, strict, full |
+| `agents` | Specialized agents | standard, strict, full |
+| `skills` | All skills (task, hybrid, knowledge) | standard, strict, full |
 | `rules-common` | Common coding rules (5 files) | standard, strict, full |
 | `rules-typescript` | TypeScript-specific rules (5 files) | auto-detect |
 | `rules-python` | Python-specific rules (5 files) | auto-detect |
@@ -4067,13 +4114,13 @@ title: "AI Toolkit - Skills Catalog"
 category: reference
 service: ai-toolkit
 tags: [skills, domain-knowledge, catalog, task-skills, hybrid-skills]
-version: "1.3.3"
+version: "1.3.8"
 created: "2026-03-23"
 last_updated: "2026-04-07"
-description: "Complete catalog of 90 skills: 28 task, 30 hybrid, 32 knowledge. Includes effort levels, skill-scoped hooks, executable scripts, security auditor, and persona presets."
+description: "Complete skills catalog with task, hybrid, and knowledge skills. Includes effort levels, skill-scoped hooks, executable scripts, security auditor, and persona presets."
 ---
 
-# Skills Catalog (90 skills)
+# Skills Catalog
 
 All functionality is unified under skills. Task and hybrid skills are user-invocable as slash commands. Knowledge skills provide domain patterns auto-loaded by agents.
 

package/llms.txt

@@ -1,6 +1,6 @@
 # ai-toolkit
 
-> Professional-grade Claude Code toolkit: 90 skills, 44 agents, machine-enforced constitution, quality hooks.
+> Professional-grade Claude Code toolkit: skills, agents, machine-enforced constitution, quality hooks.
 
 ## Documentation
 
@@ -12,9 +12,10 @@
 ## Knowledge Base
 
 - [Best Practices](kb/best-practices/README.md)
+- [No Hardcoded Counts in Secondary Docs](kb/best-practices/no-hardcoded-counts.md)
 - [How-To Guides](kb/howto/README.md)
 - [SOP: Claude Toolkit Maintenance](kb/procedures/maintenance-sop.md)
-- [Agents Catalog (44 agents)](kb/reference/agents-catalog.md)
+- [Agents Catalog](kb/reference/agents-catalog.md)
 - [Anti-Pattern Registry Format](kb/reference/anti-pattern-registry-format.md)
 - [AI Toolkit Architecture](kb/reference/architecture-overview.md)
 - [Config Benchmark](kb/reference/benchmark-config.md)
@@ -37,7 +38,7 @@
 - [Plugin Pack Conventions](kb/reference/plugin-pack-conventions.md)
 - [Quick Wins Implementation Summary](kb/reference/quick-wins-implementation-summary.md)
 - [Skill Templates](kb/reference/skill-templates.md)
-- [Skills Catalog (90 skills)](kb/reference/skills-catalog.md)
+- [Skills Catalog](kb/reference/skills-catalog.md)
 - [Skills Unification Model](kb/reference/skills-unification.md)
 - [Usage Statistics](kb/reference/stats.md)
 - [Config Sync](kb/reference/sync.md)

package/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.0.0",
+  "version": "1.3.8",
   "components": {
     "agents": {
       "description": "44 specialized agents (orchestrator, backend, frontend, security, devops, etc.)",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@softspark/ai-toolkit",
-  "version": "1.3.7",
+  "version": "1.3.9",
   "description": "Professional-grade AI coding toolkit: 90 skills, 44 agents, multi-platform support (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment), machine-enforced safety constitution, persona presets, skill security auditor, expanded lifecycle hooks, 11 plugin packs, and benchmark tooling.",
   "keywords": [
     "claude",

package/scripts/generate_augment.py

@@ -31,7 +31,7 @@ if __name__ == "__main__":
         ],
         "intro_template": (
             "This repository uses the ai-toolkit — a shared AI development toolkit"
-            " with {agents} specialized agent personas and {skills} skills."
+            " with specialized agent personas and skills."
         ),
         "agents_section": "## Available Agent Personas",
         "agents_intro": "Apply the expertise of these agents when working on relevant tasks:",

package/scripts/generate_cline.py

@@ -20,7 +20,7 @@ if __name__ == "__main__":
         ],
         "intro_template": (
             "This repository uses the ai-toolkit — a shared AI development toolkit"
-            " with {agents} specialized agent personas and {skills} skills."
+            " with specialized agent personas and skills."
         ),
         "agents_section": "## Available Agent Personas",
         "agents_intro": "Apply the expertise of these agents when working on relevant tasks:",

package/scripts/generate_copilot.py

@@ -16,7 +16,7 @@ if __name__ == "__main__":
         "title": "# GitHub Copilot Instructions",
         "intro_template": (
             "This repository uses the ai-toolkit — a shared AI development toolkit"
-            " with {agents} specialized agent personas and {skills} skills."
+            " with specialized agent personas and skills."
         ),
         "agents_section": "## Available Agent Personas",
         "agents_intro": "Apply the expertise of these agents when working on relevant tasks:",

package/scripts/generate_cursor_rules.py

@@ -20,7 +20,7 @@ if __name__ == "__main__":
         ],
         "intro_template": (
             "This repository uses the ai-toolkit — a shared AI development toolkit"
-            " with {agents} specialized agent personas and {skills} skills."
+            " with specialized agent personas and skills."
         ),
         "agents_section": "## Available Agent Personas",
         "agents_intro": "Apply the expertise of these agents when working on relevant tasks:",

package/scripts/generate_gemini.py

@@ -15,13 +15,13 @@ if __name__ == "__main__":
     render_generator({
         "title": "# AI Toolkit — Gemini CLI Configuration",
         "intro_template": (
-            "Shared AI development toolkit with {agents} specialized agents,"
-            " {skills} skills, quality hooks, and a safety constitution."
+            "Shared AI development toolkit with specialized agents,"
+            " skills, quality hooks, and a safety constitution."
         ),
-        "agents_section": "## Available Agents ({agents})",
+        "agents_section": "## Available Agents",
         "agents_intro": "Specialized agent personas — apply their expertise for relevant tasks:",
         "agents_format": "bullets",
-        "skills_section": "## Available Skills ({skills})",
+        "skills_section": "## Available Skills",
         "skills_intro": "Skills are invocable slash commands or auto-loaded knowledge sources:",
         "skills_format": "bullets",
         "guidelines": ["quality_standards", "workflow"],

package/scripts/generate_llms_txt.py

@@ -65,8 +65,8 @@ def generate_index() -> None:
     print("# ai-toolkit")
     print()
     print(
-        f"> Professional-grade Claude Code toolkit: {skills} skills,"
-        f" {agents} agents, machine-enforced constitution, quality hooks."
+        "> Professional-grade Claude Code toolkit: skills,"
+        " agents, machine-enforced constitution, quality hooks."
     )
     print()
     print("## Documentation")

package/scripts/generate_windsurf.py

@@ -20,7 +20,7 @@ if __name__ == "__main__":
         ],
         "intro_template": (
             "This repository uses the ai-toolkit — a shared AI development toolkit"
-            " with {agents} specialized agent personas and {skills} skills."
+            " with specialized agent personas and skills."
         ),
         "agents_section": "## Available Agent Personas",
         "agents_intro": "Apply the expertise of these agents when working on relevant tasks:",

package/scripts/generator_base.py

@@ -12,7 +12,7 @@ Usage::
     render_generator({
         "title": "# Cursor Rules",
         "header_lines": ["# Auto-generated..."],
-        "intro_template": "This repo uses ai-toolkit with {agents} agents and {skills} skills.",
+        "intro_template": "This repo uses ai-toolkit with specialized agents and skills.",
         "agents_section": "## Available Agent Personas",
         "agents_format": "headings",    # "headings" or "bullets"
         "agents_level": "##",           # heading level (for "headings" format)
@@ -57,7 +57,7 @@ def render_generator(config: dict) -> None:
     Config keys:
         title: str — main heading line
         header_lines: list[str] — additional header lines (comments etc)
-        intro_template: str — format string with {agents} and {skills}
+        intro_template: str — intro text (may use {agents}/{skills} placeholders)
         agents_section: str — heading for agents section
         agents_format: "headings" | "bullets"
         agents_level: str — heading level for headings format (default "##")

package/scripts/install_steps/ai_tools.py

@@ -188,39 +188,27 @@ def _inject_language_rules(cwd: Path, language_modules: list[str] | None) -> Non
     if not langs:
         return
 
-    # Build compact summary: first 5 key rules from each category
-    lines: list[str] = ["# Language Rules (auto-detected)", ""]
-    lines.append(f"Detected: **{', '.join(langs)}** + common rules.")
+    # Build a lightweight reference pointer — NOT the full rules content.
+    # Full rules are available as knowledge skills (auto-loaded by Claude)
+    # and as files Claude can Read on demand.
+    toolkit_pkg = app_dir.parent
+    lines: list[str] = ["# Language Rules", ""]
+    lines.append(f"This project uses: **{', '.join(langs)}**")
     lines.append("")
-    lines.append("Detailed rules available as knowledge skills (auto-loaded by Claude).")
-    lines.append("")
-
-    # Deduplicate: common + unique language dirs
+    lines.append("When writing or reviewing code, use the Glob and Read tools to read the rules:")
+    # Resolve actual installed path for the rules
+    rules_resolved = str(rules_src.resolve())
     all_dirs: list[str] = ["common"]
     for l in langs:
         if l not in all_dirs:
             all_dirs.append(l)
-
-    for lang_dir in all_dirs:
-        lang_path = rules_src / lang_dir
-        if not lang_path.is_dir():
-            continue
-        lang_label = lang_dir.capitalize() if lang_dir != "common" else "Common"
-        lines.append(f"## {lang_label} Rules")
-        lines.append("")
-        for rule_file in sorted(lang_path.glob("*.md")):
-            content = rule_file.read_text(encoding="utf-8").strip()
-            # Strip YAML frontmatter
-            if content.startswith("---"):
-                end = content.find("---", 3)
-                if end != -1:
-                    content = content[end + 3:].strip()
-            # Extract first 3 bullet points as key rules
-            bullets = [l.strip() for l in content.splitlines() if l.strip().startswith("- ")][:3]
-            if bullets:
-                category = rule_file.stem.replace("-", " ").title()
-                lines.append(f"**{category}:** {' | '.join(b.lstrip('- ') for b in bullets)}")
-        lines.append("")
+    for lang in all_dirs:
+        lang_path = rules_src / lang
+        if lang_path.is_dir():
+            categories = ", ".join(f.stem for f in sorted(lang_path.glob("*.md")))
+            lines.append(f"- `{lang_path.resolve()}/` ({categories})")
+    lines.append("")
+    lines.append("Read the relevant rule files before making code changes. Do NOT guess — read first.")
 
     # Write summary to temp file, then inject as section
     import tempfile