@softspark/ai-toolkit 4.11.0 → 4.13.0

package/kb/reference/claude-ecosystem-expansion-foundations.md

@@ -3,9 +3,9 @@ title: "Claude Ecosystem Expansion Foundations"
 category: reference
 service: ai-toolkit
 tags: [benchmark, claude-code, ecosystem, hooks, plugins, architecture]
-version: "1.0.0"
+version: "1.1.0"
 created: "2026-03-27"
-last_updated: "2026-04-13"
+last_updated: "2026-07-10"
 description: "Reference summary of the ecosystem signals and implementation foundations adopted in ai-toolkit, including runtime-aware plugin packaging."
 ---
 
@@ -25,14 +25,22 @@ The outcome is a toolkit that is now positioned as a more modular, Claude-first,
 
 ### 1. Plugin-oriented structure
 
-`ai-toolkit` now treats plugin packaging as a first-class capability, with runtime-aware install surfaces for Claude and optional global Codex layering.
+`ai-toolkit` now treats plugin packaging as a first-class capability, with separate runtime-aware surfaces for Claude Code, the Claude Chat/Desktop/Cowork app, and optional global Codex layering.
 
 Implemented artifacts:
 - `app/.claude-plugin/plugin.json`
+- `app/claude-app/`
 - `app/plugins/`
 - `app/skills/plugin-creator/SKILL.md`
+- `scripts/claude_app.py`
 - `kb/reference/plugin-pack-conventions.md`
 
+Claude Code reads filesystem configuration such as `~/.claude/rules` and
+`CLAUDE.md`. The Claude app does not scan those locations. For the app,
+`ai-toolkit claude-app export --verify` creates an uploadable plugin ZIP and a
+separate Cowork global-instructions file. Plugin skills work in Chat and Cowork;
+hooks and sub-agents are Cowork-only.
+
 ### 2. Broader lifecycle coverage
 
 The toolkit now covers prompt, edit, subagent, compaction, and session-end phases.
@@ -85,6 +93,7 @@ The reference benchmark set is intentionally curated:
 | Area | Adopted in ai-toolkit |
 |------|------------------------|
 | Plugin manifests | Yes |
+| Claude Chat/Cowork uploadable plugin export | Yes |
 | Domain plugin packs | Yes (experimental) |
 | Hook creator workflow | Yes |
 | Command creator workflow | Yes |

package/kb/reference/cli-reference.md

@@ -4,7 +4,7 @@ category: reference
 service: ai-toolkit
 tags: [cli, commands, reference, install, update, plugin, mcp, telemetry]
 created: "2026-04-13"
-last_updated: "2026-04-24"
+last_updated: "2026-07-10"
 description: "Complete CLI reference for all ai-toolkit commands, options, and flags."
 ---
 
@@ -29,6 +29,8 @@ Usage: ai-toolkit <command> [options]
 | `doctor` | Diagnose install health, hooks, quick-win assets, and artifact drift |
 | `doctor --fix` | Auto-repair broken symlinks, missing hooks, stale artifacts |
 | `eject [dir]` | Export standalone config (no symlinks, no toolkit dependency) |
+| `claude-app export [--output FILE] [--no-custom-rules] [--verify]` | Build an uploadable Claude Chat/Desktop/Cowork plugin ZIP and global-instructions file |
+| `claude-app verify` | Validate a clean staged plugin with structural checks and the official Claude plugin validator |
 
 ## Rule & Hook Injection
 
@@ -55,7 +57,7 @@ Usage: ai-toolkit <command> [options]
 | Command | Description |
 |---------|-------------|
 | `plugin list` | Show available plugin packs with install status |
-| `plugin install <name> [--editor claude\|codex\|all]` | Install a plugin pack for selected runtime(s) |
+| `plugin install <name> [--editor claude\|codex\|all]` | Install a plugin pack for Claude Code and/or Codex (`claude` means Claude Code, not the Claude app) |
 | `plugin install --all [--editor claude\|codex\|all]` | Install all 11 plugin packs |
 | `plugin update <name> [--editor claude\|codex\|all]` | Update a plugin pack (remove + reinstall, preserves data) |
 | `plugin update --all [--editor claude\|codex\|all]` | Update all installed plugin packs |

package/kb/reference/codex-cli-compatibility.md

@@ -29,8 +29,7 @@ model.
 
 `ai-toolkit install --local --editors codex` generates:
 
-- `AGENTS.md`
-- `.agents/rules/*.md`
+- `AGENTS.md` (project root; universal coding rules inlined — Codex reads instructions only from AGENTS.md, not `.agents/rules/`)
 - `.agents/skills/*`
 - `.codex/hooks.json`
 
@@ -38,8 +37,7 @@ model.
 
 `ai-toolkit plugin install --editor codex <pack>` bootstraps or reuses:
 
-- `~/AGENTS.md`
-- `~/.agents/rules/*.md`
+- `~/.codex/AGENTS.md` (the documented global instruction file; pack rules are marker-injected here, not written as unread `~/.agents/rules/` files)
 - `~/.agents/skills/*`
 - `~/.codex/hooks.json`
 
@@ -93,20 +91,27 @@ The adapter also covers skills that previously depended only on Claude's
 
 ## Hook Compatibility
 
-Codex does not expose the full Claude hook event surface. The Codex hook
-generator emits only the events supported by Codex runtime integration:
+Codex does not expose the full Claude hook event surface. Codex's
+`HookEventName` enum defines 10 events; the Codex hook generator wires 9 of
+them:
 
 - `SessionStart`
 - `PreToolUse`
 - `PostToolUse`
+- `PermissionRequest`
 - `UserPromptSubmit`
+- `SubagentStart`
+- `SubagentStop`
+- `PreCompact`
 - `Stop`
 
-This means Claude-only events such as `TaskCompleted`, `TeammateIdle`,
-`SubagentStart`, `SubagentStop`, `PreCompact`, `SessionEnd`, and
-`Notification` are not available in `.codex/hooks.json`.
+`PostCompact` is the one enum event left unwired (its only hook was the removed
+environment-snapshot probe). Claude-only events such as `TaskCompleted`,
+`TeammateIdle`, `SessionEnd`, and `Notification` have no Codex equivalent and
+are not available in `.codex/hooks.json`. Handler types: only `command` runs;
+`prompt` and `agent` are parsed by Codex but not yet executed.
 
-`inject-hook` automatically propagates Codex-compatible events to
+`inject-hook` automatically propagates these 9 Codex-compatible events to
 `~/.codex/hooks.json` (global layer). Non-Codex events are silently skipped.
 `remove-hook` cleans both Claude and Codex targets.
 

package/kb/reference/global-install-model.md

@@ -3,10 +3,10 @@ title: "Global Install Model"
 category: reference
 service: ai-toolkit
 tags: [install, global, claude, codex, plugins, local-setup]
-version: "3.1.0"
+version: "3.2.0"
 created: "2026-03-26"
-last_updated: "2026-06-30"
-description: "Reference description of the global install target, project-local editor setup, global Codex plugin layering, and command responsibilities in ai-toolkit."
+last_updated: "2026-07-10"
+description: "Reference description of Claude Code global install, Claude app plugin export, project-local editor setup, global Codex plugin layering, and command responsibilities in ai-toolkit."
 ---
 
 # Global Install Model
@@ -24,6 +24,10 @@ the core toolkit install, but experimental plugin packs can layer a global
 Codex target in `HOME` when explicitly installed with
 `ai-toolkit plugin install --editor codex`.
 
+Claude Chat/Desktop/Cowork is a separate runtime. It does not read the
+filesystem surfaces under `~/.claude`; it receives ai-toolkit through an
+uploaded plugin plus app-managed global/folder instructions.
+
 ## Command Responsibilities
 
 | Command | Target | Purpose |
@@ -34,6 +38,7 @@ Codex target in `HOME` when explicitly installed with
 | `ai-toolkit install --local --lang <lang>` | current project | explicit language selection for rules (e.g. `--lang typescript`, `--lang go,python`); auto-detected when omitted |
 | `ai-toolkit install --modules <list>` | `~/.claude/` | selective module install (e.g. `--modules core,agents,rules-typescript`) |
 | `ai-toolkit update --local` | current project | refresh project configs; auto-detects editors from existing files |
+| `ai-toolkit claude-app export` | ZIP + Markdown output | build the uploadable Claude Chat/Cowork plugin and Cowork global instructions; registered rules are included unless `--no-custom-rules` is set |
 | `ai-toolkit add-rule` | `~/.softspark/ai-toolkit/rules/` | register a global rule |
 | `ai-toolkit remove-rule` | `~/.softspark/ai-toolkit/rules/` | unregister a global rule |
 | `ai-toolkit mcp add <name...>` | current project | merge MCP templates into `.mcp.json` |
@@ -70,19 +75,41 @@ Claude Code's default global install writes these managed surfaces:
 
 The `ai-toolkit-*` prefix in `~/.claude/rules/` is reserved for installer-managed files. User-authored Claude rules should use another filename prefix, or be registered through `ai-toolkit add-rule` so they are emitted as `ai-toolkit-registered-*.md`.
 
+## Claude App Target
+
+`~/.claude/` is a Claude Code surface, not a Claude Chat/Cowork surface. Run:
+
+```bash
+ai-toolkit claude-app export --verify
+```
+
+Upload the ZIP from `Customize > Plugins`, then paste the sibling
+`*-global-instructions.md` file into `Settings > Cowork > Global instructions`.
+The plugin contains the normal skills and agents, app-relative Cowork hooks,
+and an `ai-toolkit-rules` skill generated from common/standalone rules.
+Registered rules are embedded in a separate skill by default. Skills work in
+Chat and Cowork; hooks and sub-agents are Cowork-only. The app owns its plugin
+store, so toolkit updates require re-export and re-upload.
+
 `ai-toolkit install --editors <name>` can write global files only for editors
 with documented, file-based config surfaces:
 
-- `windsurf`: `~/.codeium/windsurf/memories/global_rules.md` plus `~/.codeium/windsurf/skills/ai-toolkit-skill-catalogue/SKILL.md`
-- `gemini`: `~/.gemini/GEMINI.md`
-- `augment`: `~/.augment/rules/ai-toolkit.md`
+- `windsurf`: `~/.codeium/windsurf/memories/global_rules.md` plus `~/.codeium/windsurf/skills/ai-toolkit-skill-catalogue/SKILL.md` plus `~/.config/devin/AGENTS.md` (Devin CLI global rules — the Desktop `global_rules.md` path is not imported by `read_config_from.windsurf`)
+- `gemini`: `~/.gemini/GEMINI.md`; hooks at `~/.gemini/settings.json` (profile ≥ standard); `~/.gemini/commands/` and `~/.gemini/skills/` pointer (profile full)
+- `augment`: `~/.augment/rules/ai-toolkit.md`; `~/.augment/agents/`, `~/.augment/commands/`, and hooks in `~/.augment/settings.json` (profile full)
 - `cline`: `~/Documents/Cline/Rules/ai-toolkit-*.md` plus `~/.cline/skills/ai-toolkit-skill-catalogue/SKILL.md`
-- `roo`: `~/.roo/rules/ai-toolkit-*.md`
+- `roo`: `~/.roo/rules/ai-toolkit-*.md` plus `~/.agents/skills/*` (Roo/Zoo native skill discovery; skipped when `codex` is also selected, which fills the same dir)
 - `aider`: `~/.aider.conf.yml` plus `~/.aider-ai-toolkit-CONVENTIONS.md` when the YAML file does not already exist
-- `codex`: `~/AGENTS.md` (coding rules inlined), `~/.agents/skills/*`, `~/.codex/hooks.json`
+- `codex`: `~/.codex/AGENTS.md` (coding rules inlined; the documented global instruction file — NOT `~/AGENTS.md`, which Codex never loads as global instructions), `~/.agents/skills/*`, `~/.codex/hooks.json`
 - `opencode`: `~/.config/opencode/*`
 
-Cursor, GitHub Copilot, and Google Antigravity rule installs stay project-local.
+Cursor, GitHub Copilot, and Google Antigravity now have partial global support,
+scoped to whatever documented HOME file surface each exposes:
+
+- `cursor`: `~/.cursor/hooks.json` (safety/quality hooks; profile ≥ standard). Cursor RULES stay project-local — their only global surface is the Settings UI.
+- `copilot`: `~/.copilot/copilot-instructions.md` plus `~/.copilot/instructions/ai-toolkit-*.instructions.md` (read by Copilot CLI; VS Code and GitHub.com still use repo `.github/` files, which the local install emits).
+- `antigravity`: skill pointer at `~/.gemini/config/skills/` and `~/.gemini/antigravity-cli/skills/`. Antigravity RULES stay project-local.
+
 Their global MCP support, where available, is handled by `ai-toolkit mcp
 install`, not by the rule installer.
 
@@ -141,8 +168,7 @@ Codex wrappers so the project still receives the full skill catalog.
 
 `ai-toolkit plugin install --editor codex <pack>` additionally targets:
 
-- `~/AGENTS.md`
-- `~/.agents/rules/*.md`
+- `~/.codex/AGENTS.md` (base instructions; pack rules are marker-injected here, not written as unread `~/.agents/rules/` files)
 - `~/.agents/skills/*`
 - `~/.codex/hooks.json`
 

package/kb/reference/hooks-catalog.md

@@ -13,7 +13,7 @@ description: "Complete reference of all ai-toolkit hooks: events, scripts, insta
 
 ## Overview
 
-ai-toolkit provides 29 global hook entries across 14 lifecycle events that enforce quality, safety, and workflow rules across all Claude Code sessions. Hooks are merged into `~/.claude/settings.json` on install, with logic in standalone scripts at `~/.softspark/ai-toolkit/hooks/`.
+ai-toolkit provides 28 global hook entries across 14 lifecycle events that enforce quality, safety, and workflow rules across all Claude Code sessions, plus a separate `statusLine` command. Hooks are merged into `~/.claude/settings.json` on install, with logic in standalone scripts at `~/.softspark/ai-toolkit/hooks/`.
 
 ## Supported Surface
 
@@ -575,14 +575,13 @@ Beyond the global Claude Code hooks above, full-profile project installs emit na
 | Editor | File | Generator | Format |
 |--------|------|-----------|--------|
 | Cursor | `.cursor/hooks.json` | `generate_cursor_hooks.py` | Cursor hooks schema |
-| Windsurf (Cascade) | `.windsurf/hooks.json` | `generate_windsurf_hooks.py` | Cascade `agent_action_name`/`tool_info` — **deprecated, dies 2026-07-01** |
 | Devin CLI | `.devin/hooks.v1.json` | `generate_devin_hooks.py` | Claude-compatible (the replacement for Cascade) |
 | Gemini CLI | `.gemini/settings.json` (hooks block) | `generate_gemini_hooks.py` | Gemini `BeforeTool`/`AfterTool` events |
 | Augment | `.augment/settings.json` (hooks block) | `generate_augment_hooks.py` | Claude-style events |
 
 ### Devin CLI hooks (`.devin/hooks.v1.json`)
 
-Windsurf rebranded to Devin Desktop (2026-06-02); the Cascade agent — and its `.windsurf/hooks.json` surface — is available only through **2026-07-01**. Devin Local / Devin CLI do **not** read `.windsurf/hooks.json` as a fallback, so hooks must be regenerated onto the Devin CLI format.
+Windsurf rebranded to Devin Desktop (2026-06-02). The Cascade hook surface ended on 2026-07-01; ai-toolkit now emits only the live Devin CLI format.
 
 Devin CLI uses a **Claude-compatible** hook format (docs.devin.ai/cli/extensibility/hooks). Key facts driving the generator:
 

package/kb/reference/plugin-pack-conventions.md

@@ -6,14 +6,14 @@ tags: [plugins, plugin-packs, conventions, manifests, hooks, policy-packs]
 version: "1.0.0"
 created: "2026-03-28"
 last_updated: "2026-04-13"
-description: "Conventions for experimental ai-toolkit plugin packs, policy packs, hook packs, and plugin-creator scaffolding across Claude and Codex runtimes."
+description: "Conventions for experimental ai-toolkit plugin packs, policy packs, hook packs, and plugin-creator scaffolding across Claude Code and Codex runtimes."
 ---
 
 # Plugin Pack Conventions
 
 ## Purpose
 
-`ai-toolkit` now includes experimental plugin packs under `app/plugins/` to formalize a runtime-aware plugin direction for Claude and optional global Codex layering without changing the default core install surface.
+`ai-toolkit` includes experimental plugin packs under `app/plugins/` for Claude Code and optional global Codex layering. These internal pack manifests are distinct from the official uploadable Claude app plugin built by `ai-toolkit claude-app export`.
 
 ## Pack Types
 
@@ -73,7 +73,7 @@ Required keys:
 
 ```bash
 ai-toolkit plugin list               # show all 11 packs with install status
-ai-toolkit plugin install --editor claude <name>   # Claude global target
+ai-toolkit plugin install --editor claude <name>   # Claude Code global target
 ai-toolkit plugin install --editor codex <name>    # Codex global target
 ai-toolkit plugin install --editor all --all       # install all 11 packs for both runtimes
 ai-toolkit plugin update --editor all --all        # update all installed packs
@@ -90,7 +90,7 @@ ai-toolkit plugin status --editor all              # show installed packs with r
 2. **Copies** plugin-specific hooks to `~/.softspark/ai-toolkit/hooks/plugin-<pack>-<hook>.sh`
 3. **Copies** plugin-specific scripts to `~/.softspark/ai-toolkit/plugin-scripts/<pack>/`
 4. **Runs** init scripts if present (e.g. `init_db.py` for memory-pack — safe to re-run, preserves data)
-5. **Claude target**: links missing agents/skills into `~/.claude/`, injects plugin-local rules into `~/.claude/CLAUDE.md`, and merges plugin hook entries into `~/.claude/settings.json`
+5. **Claude Code target**: links missing agents/skills into `~/.claude/`, injects plugin-local rules into `~/.claude/CLAUDE.md`, and merges plugin hook entries into `~/.claude/settings.json`
 6. **Codex target**: bootstraps global Codex assets in `HOME` (`~/AGENTS.md`, `~/.agents/skills`, `~/.agents/rules`, `~/.codex/hooks.json`) and then layers plugin-specific rules/hooks on top
 7. **Records** installed state per runtime in `~/.softspark/ai-toolkit/plugins.json`
 
@@ -110,7 +110,7 @@ ai-toolkit plugin status --editor all              # show installed packs with r
 
 ### What `plugin remove` Does
 
-1. **Claude target**: strips plugin hook entries from `~/.claude/settings.json` and removes plugin-local rule sections from `~/.claude/CLAUDE.md`
+1. **Claude Code target**: strips plugin hook entries from `~/.claude/settings.json` and removes plugin-local rule sections from `~/.claude/CLAUDE.md`
 2. **Codex target**: strips plugin hook entries from `~/.codex/hooks.json` and removes `~/.agents/rules/plugin-<pack>-*.md`
 3. **Shared assets** (`~/.softspark/ai-toolkit/hooks/plugin-*`, `plugin-scripts/<pack>/`) are removed only when no remaining runtime still uses that pack
 4. **Updates** `plugins.json` state per runtime

package/kb/reference/skills-catalog.md

@@ -254,6 +254,8 @@ Step 0 interview before setup — 5 targeted questions to capture undocumented p
 
 Codex CLI receives the full skill catalog during `ai-toolkit install --local --editors codex`.
 
+Claude Chat/Desktop/Cowork receives this same catalog through `ai-toolkit claude-app export`. The export also adds an app-only `ai-toolkit-rules` skill because the Claude app does not read Claude Code's `CLAUDE.md` or `.claude/rules/` surfaces.
+
 - Native Codex-compatible skills are symlinked directly into `.agents/skills/`
 - Claude-oriented orchestration skills are generated as Codex wrappers
 - Adapted wrappers translate `Agent`, `Team*`, and `Task*` guidance to `spawn_agent`, `send_input`, `wait_agent`, `close_agent`, and `update_plan`

package/kb/reference/supported-tools-registry.md

@@ -3,19 +3,19 @@ title: "Supported Tools Registry"
 category: reference
 service: ai-toolkit
 tags: [editors, platforms, generators, integration, ecosystem]
-version: "1.7.1"
+version: "1.8.0"
 created: "2026-04-23"
-last_updated: "2026-06-30"
-description: "Human-readable view of scripts/ecosystem_tools.json — the canonical list of tools ai-toolkit integrates with (Claude Code + 11 editors), their documentation URLs, config paths, our generators, and tracked capability markers."
+last_updated: "2026-07-10"
+description: "Human-readable view of scripts/ecosystem_tools.json — the canonical list of tools ai-toolkit integrates with (Claude Code, Claude Chat/Cowork, and 11 editors), their documentation URLs, config paths, our generators, and tracked capability markers."
 ---
 
 # Supported Tools Registry
 
 The canonical data lives in **`scripts/ecosystem_tools.json`** and is consumed by `scripts/ecosystem_doctor.py`. This document is a derived view — when the JSON changes, update this table too.
 
-## Tool Count: 12
+## Tool Count: 13
 
-1 primary runtime (Claude Code) + 11 editor integrations.
+1 primary runtime (Claude Code) + 1 Claude app target + 11 editor integrations.
 
 ---
 
@@ -28,7 +28,7 @@ The canonical data lives in **`scripts/ecosystem_tools.json`** and is consumed b
 | ID | `claude-code` |
 | Docs | https://code.claude.com/docs (platform.claude.com/docs 307-redirects here) |
 | Release notes | https://github.com/anthropics/claude-code/releases |
-| Changelog | https://code.claude.com/docs/en/changelog (lists current 2.1.186) |
+| Changelog | https://code.claude.com/docs/en/changelog; GitHub release feed is authoritative when the generated page lags (current local/release: 2.1.206, 2026-07-10) |
 | Config paths | `~/.claude/settings.json`, `.claude/settings.json` (project, committed), `.claude/settings.local.json`, `CLAUDE.md`, `.claude/rules/*.md`, `.claude/agents/*.md`, `.claude/skills/*/SKILL.md`, `~/.claude/themes/*.json` (v2.1.118+) |
 | Our generators | — (Claude Code is the primary target; toolkit content ships directly as `.md` files and `settings.json` merges) |
 | Tracked hook events | Core: `SessionStart`, `SessionEnd`, `UserPromptSubmit`, `Notification`, `MessageDisplay`. Tool: `PreToolUse`, `PostToolUse`, `PostToolUseFailure`, `PostToolBatch`. Turn: `Stop`, `StopFailure`, `UserPromptExpansion`. Subagent: `SubagentStart`, `SubagentStop`. Compaction: `PreCompact`, `PostCompact`. Permissions: `PermissionRequest`, `PermissionDenied`. Elicitation: `Elicitation`, `ElicitationResult`. Teams: `TaskCreated`, `TaskCompleted`, `TeammateIdle`. Worktrees/env: `WorktreeCreate`, `WorktreeRemove`, `CwdChanged`, `FileChanged`, `ConfigChange`. Setup: `Setup`, `InstructionsLoaded` |
@@ -39,6 +39,23 @@ The canonical data lives in **`scripts/ecosystem_tools.json`** and is consumed b
 
 ---
 
+## Claude App Target
+
+### Claude Chat / Cowork
+
+| Field | Value |
+|-------|-------|
+| ID | `claude-app` |
+| Docs | https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork |
+| Plugin docs | https://support.claude.com/en/articles/13837440-use-plugins-in-claude |
+| Config surfaces | `Settings > Cowork > Global instructions`, Cowork folder instructions, `Customize > Skills`, and `Customize > Plugins` |
+| Plugin layout | `.claude-plugin/plugin.json`, `skills/*/SKILL.md`, `agents/*.md`, `hooks/hooks.json`; ai-toolkit uses manifest paths under `claude-app/` for its generated app-only rules and hooks |
+| Our generator | `scripts/claude_app.py` (`ai-toolkit claude-app export`) |
+| Runtime split | Skills work in Chat (web/Desktop) and Cowork. Hooks and sub-agents run only in Cowork. Claude app does **not** scan Claude Code's `~/.claude/rules/`, `CLAUDE.md`, or `~/.claude/settings.json`. |
+| Install/update | Export the ZIP, upload it from `Customize > Plugins`, then paste the generated global-instructions file into `Settings > Cowork > Global instructions`. Re-export/re-upload after toolkit updates. |
+
+---
+
 ## Editor Integrations
 
 ### Cursor
@@ -49,9 +66,10 @@ The canonical data lives in **`scripts/ecosystem_tools.json`** and is consumed b
 | Docs | https://cursor.com/docs |
 | Changelog | https://cursor.com/changelog |
 | Stable docs mirror | https://cursor.com/llms.txt (all doc pages have .md twins) |
-| Config paths | `.cursorrules`, `.cursor/rules/*.mdc` (plain `.md` files in `.cursor/rules/` are **ignored** by the rules system), `AGENTS.md`, `.cursor/mcp.json`, `~/.cursor/mcp.json`, `.cursor/skills/*/SKILL.md`, `~/.cursor/skills/*/SKILL.md`, `.cursor/agents/*.md`, `~/.cursor/agents/*.md`, `.cursor/hooks.json` |
+| Config paths | `.cursorrules` (**legacy** — no longer in cursor.com/docs/rules; deprecated ~0.43–0.45 in favor of `.cursor/rules/*.mdc`, still read, no removal deadline; we keep emitting for back-compat), `.cursor/rules/*.mdc` (plain `.md` files in `.cursor/rules/` are **ignored** by the rules system), `AGENTS.md`, `.cursor/mcp.json`, `~/.cursor/mcp.json`, `.cursor/hooks.json`, `~/.cursor/hooks.json` (user-level hooks scope; enterprise system paths + dashboard team hooks not adopted, class C), `.cursor/skills/*/SKILL.md`, `~/.cursor/skills/*/SKILL.md`, `.cursor/agents/*.md`, `~/.cursor/agents/*.md` |
 | Compat read paths | skills: `.agents/skills/`, `~/.agents/skills/`, `.claude/skills/`, `~/.claude/skills/`, `.codex/skills/`, `~/.codex/skills/`; subagents: `.claude/agents/`, `~/.claude/agents/`, `.codex/agents/`, `~/.codex/agents/` (`.cursor/` wins on name conflicts) |
-| Our generators | `scripts/generate_cursor_rules.py`, `scripts/generate_cursor_mdc.py`, `scripts/generate_cursor_hooks.py` (profile=full), `scripts/generate_cursor_agents.py` (profile=full), `scripts/generate_cursor_skills.py` (profile=full pointer) |
+| Our generators | `scripts/generate_cursor_rules.py`, `scripts/generate_cursor_mdc.py`, `scripts/generate_cursor_hooks.py` (profile=full local **and** global `~/.cursor/hooks.json`), `scripts/generate_cursor_agents.py` (profile=full), `scripts/generate_cursor_skills.py` (profile=full pointer) |
+| Global install | Cursor is in `GLOBAL_CAPABLE_EDITORS` for **hooks only**: `ai-toolkit install --editors cursor` writes `~/.cursor/hooks.json` (profile ≥ standard). RULES stay project-local (Cursor's only global rules surface is the Settings UI). |
 | Tracked capabilities | `cursorrules`, `.cursor/rules`, `AGENTS.md`, `mcp.json`, Composer, Agent Mode, hooks.json, subagents, skills, plugins |
 
 ### Windsurf
@@ -61,14 +79,15 @@ The canonical data lives in **`scripts/ecosystem_tools.json`** and is consumed b
 | ID | `windsurf` |
 | Docs | https://docs.devin.ai/desktop (Windsurf rebranded to Devin Desktop ~2026-06-02; docs.windsurf.com resolves here) |
 | Changelog | https://docs.devin.ai/desktop/changelog (windsurf.com/changelog 308-permanent-redirects here) |
-| Stable docs mirror | https://docs.devin.ai/desktop/... per-page .md twins; legacy `.windsurf/`, `.windsurfrules`, `~/.codeium/windsurf/` paths still read as fallback (new canonical: `.devin/`) |
-| Config paths | **Primary (Devin Desktop):** `.devin/rules/*.md`, `.devin/workflows/*.md`, `.devin/skills/*/SKILL.md`, `.devin/hooks.v1.json` (Devin CLI hooks, Claude format), `.devin/config.json`, `.devin/config.local.json`, `~/.config/devin/config.json` (Devin Local MCP/permissions). **Legacy fallback:** `.windsurfrules`, `.windsurf/rules/*.md`, `.windsurf/workflows/*.md`, `.windsurf/skills/*/SKILL.md`, `~/.codeium/windsurf/memories/global_rules.md`, `~/.codeium/windsurf/skills/*/SKILL.md`, `~/.codeium/windsurf/mcp_config.json`. Plus `AGENTS.md`. |
-| Compat read paths | skills: `.agents/skills/`, `~/.agents/skills/`, (with Claude Code config-reading) `.claude/skills/`, `~/.claude/skills/`. **Hooks: Devin CLI reads `.claude/settings.json` + `~/.claude/settings.json` hooks directly (`read_config_from.claude` default on), so globally-installed toolkit hooks work under Devin with no project-local file.** |
-| Our generators | `scripts/generate_windsurf.py`, `scripts/generate_windsurf_rules.py` (dual-emits `.devin/` + `.windsurf/`), `scripts/generate_windsurf_hooks.py` (profile=full; **Cascade-scoped, deprecated, drop after 2026-07-01**), `scripts/generate_devin_hooks.py` (profile=full; `.devin/hooks.v1.json`, Claude-format Devin CLI hooks), `scripts/generate_windsurf_skills.py` (global + profile=full pointer, dual-emits) |
+| Stable docs mirror | https://docs.devin.ai/desktop/... per-page .md twins; legacy `.windsurf/`, `.windsurfrules`, `~/.codeium/windsurf/` rule paths still read as fallback (new canonical rules/hooks tree: `.devin/`) |
+| Config paths | **Primary (Devin Desktop):** `.devin/rules/*.md`, `.devin/workflows/*.md`, `.devin/hooks.v1.json` (Devin CLI hooks, Claude format), `.devin/config.json`, `.devin/config.local.json`, `~/.config/devin/config.json` (Devin Local MCP/permissions). **Skills:** eight documented paths, all scanned in every repo — `.agents/skills/*/SKILL.md` (recommended), `.devin/skills`, `.github/skills`, `.claude/skills`, `.cursor/skills`, `.codex/skills`, `.cognition/skills`, and `.windsurf/skills`. ai-toolkit emits a single canonical pointer under `.windsurf/skills` to avoid duplicate registration. **Legacy fallback:** `.windsurfrules`, `.windsurf/rules/*.md`, `.windsurf/workflows/*.md`, `~/.codeium/windsurf/memories/global_rules.md`, `~/.codeium/windsurf/skills/*/SKILL.md`, `~/.codeium/windsurf/mcp_config.json`. Plus `AGENTS.md`. |
+| Compat read paths | Current skill docs explicitly scan all eight paths — `.agents/skills/`, `.devin/skills/`, `.github/skills/`, `.claude/skills/`, `.cursor/skills/`, `.codex/skills/`, `.cognition/skills/`, and `.windsurf/skills/`. **Hooks:** Devin CLI reads `.claude/settings.json` + `~/.claude/settings.json` hooks when `read_config_from.claude` is enabled, so globally-installed toolkit hooks also work under Devin. |
+| Our generators | `scripts/generate_windsurf.py`, `scripts/generate_windsurf_rules.py` (dual-emits `.devin/` + `.windsurf/` rules/workflows), `scripts/generate_devin_hooks.py` (profile=full; `.devin/hooks.v1.json`), `scripts/generate_windsurf_skills.py` (`.windsurf/skills` pointer) |
+| Global install | `ai-toolkit install --editors windsurf` writes `~/.codeium/windsurf/memories/global_rules.md` + skills pointer **and** `~/.config/devin/AGENTS.md` (Devin CLI global rules — the Desktop `global_rules.md` path is absent from `read_config_from.windsurf`, so editor-only Devin CLI installs need this). |
 | Tracked capabilities | Cascade, `windsurfrules`, `AGENTS.md`, activation triggers (`always_on`/`glob`/`model_decision`), workflows, skills, MCP, memories, hooks |
 | Activation modes emitted | always_on (agents/security/quality), glob (testing + language rules), model_decision (code-style/workflow) |
-| Hooks migration | **Done.** Cascade `.windsurf/hooks.json` (`agent_action_name`/`tool_info` format) dies 2026-07-01 with no Devin fallback. `generate_devin_hooks.py` emits `.devin/hooks.v1.json` in the Claude-compatible format Devin CLI uses: Claude-style events (PreToolUse/PostToolUse/UserPromptSubmit/Stop/SessionStart), matchers on Devin tool names (`read`/`edit`/`exec`/`mcp__*`), blocking via flat `{"decision":"block","reason":...}` + exit 2 (no `AI_TOOLKIT_HOOK_FORMAT=json` — Devin does not use Claude's `hookSpecificOutput` envelope). `post_setup_worktree`→`SessionStart`; `post_cascade_response`→`Stop` (no response text on stdin). Both hook generators run at profile=full during the transition; drop `generate_windsurf_hooks.py` in the first release after 2026-07-01. |
-| Sunset notes | Cascade agent is available only through **2026-07-01**; Devin Local is the default agent since 2026-06-02. Devin CLI ("Devin for Terminal") shares the Devin Local harness, reads `AGENTS.md`, the standard `SKILL.md` format, and Claude-format hooks; not yet a separate registry entry. |
+| Hooks migration | **Complete.** Cascade and `.windsurf/hooks.json` ended on 2026-07-01. `generate_devin_hooks.py` is now the only Windsurf-family hook generator and emits `.devin/hooks.v1.json` with Claude-style events, Devin tool-name matchers, and the flat Devin block contract. |
+| Latest upstream | Devin Desktop v3.4.27 (2026-07-07). v3.4.22 made skill `permissions:` frontmatter affect auto-approvals; ai-toolkit does not emit permissions because its pointer skill executes no privileged workflow. |
 
 ### GitHub Copilot
 
@@ -77,9 +96,11 @@ The canonical data lives in **`scripts/ecosystem_tools.json`** and is consumed b
 | ID | `github-copilot` |
 | Docs | https://docs.github.com/en/copilot |
 | Release notes | https://github.blog/changelog/label/copilot/ |
-| Config paths | `.github/copilot-instructions.md`, `.github/instructions/*.instructions.md`, `.github/prompts/*.prompt.md`, `AGENTS.md` |
-| Our generators | `scripts/generate_copilot.py` |
-| Tracked capabilities | `copilot-instructions.md`, Copilot Chat, Copilot Workspace, Copilot cloud agent, `applyTo`, custom agents, prompt files, `instructions.md`, `AGENTS.md`, MCP |
+| Config paths | **Repo (`.github/`):** `.github/copilot-instructions.md`, `.github/instructions/*.instructions.md`, `.github/prompts/*.prompt.md`, `AGENTS.md`, `.github/hooks/*.json`. **Copilot CLI user-level (`~/.copilot/`, `COPILOT_HOME` override):** `~/.copilot/copilot-instructions.md`, `~/.copilot/instructions/*.instructions.md`, `~/.copilot/agents/*.agent.md`, `~/.copilot/skills/<name>/SKILL.md`, `~/.copilot/hooks/`, `~/.copilot/settings.json`, `~/.copilot/mcp-config.json` |
+| Compat read paths | skills: Copilot CLI reads personal `~/.copilot/skills` and `~/.agents/skills` (the latter populated by our codex/roo global installs) and project `.github/skills`, `.claude/skills`, `.agents/skills` — so toolkit skills are already Copilot-visible. (Note: since CLI 1.0.61 a session using `COPILOT_HOME`/`--config-dir` stops reading `~/.agents/skills`.) |
+| Our generators | `scripts/generate_copilot.py` (repo `.github/` and, with `config_root=~/.copilot`, global CLI instructions) |
+| Global install | Copilot is in `GLOBAL_CAPABLE_EDITORS`: `ai-toolkit install --editors copilot` writes `~/.copilot/copilot-instructions.md` + `~/.copilot/instructions/ai-toolkit-*.instructions.md` (read by Copilot CLI). VS Code Copilot uses profile-level locations and GitHub.com uses repo files, so the project `.github/` emission stays. |
+| Tracked capabilities | `copilot-instructions.md`, Copilot Chat, Copilot Workspace, Copilot cloud agent, `applyTo`, custom agents, prompt files, `instructions.md`, `AGENTS.md`, MCP, skills, CLI hooks, `~/.copilot/` |
 | Tier notes | Custom agents (`.github/agents/*.agent.md`) and repo-level MCP config are Pro/Pro+/Business/Enterprise only and intentionally not integrated (class C per ecosystem-sync SOP). Copilot code review reads the nearest `AGENTS.md` automatically since the 2026-06-18 GA (all tiers); `ai-toolkit install --local --editors copilot` injects a `TOOLKIT:copilot-agents` section generated from `generate_agents_md.py` without clobbering Codex/opencode sections in the same file. The 4000-char cap on `copilot-instructions.md` / `*.instructions.md` was also removed (2026-06-12). |
 
 ### Gemini CLI
@@ -91,9 +112,10 @@ The canonical data lives in **`scripts/ecosystem_tools.json`** and is consumed b
 | Release notes | https://github.com/google-gemini/gemini-cli/releases |
 | Config paths | `GEMINI.md`, `.gemini/settings.json`, `~/.gemini/settings.json`, `.gemini/commands/*.toml`, `.gemini/skills/*/SKILL.md`, `.agents/skills/*/SKILL.md`, `~/.gemini/skills/*/SKILL.md`, `~/.agents/skills/*/SKILL.md` (the `.agents/skills` alias wins over `.gemini/skills` within the same tier), `.gemini/extensions/gemini-extension.json` |
 | Our generators | `scripts/generate_gemini.py`, `scripts/generate_gemini_hooks.py` (profile>=standard), `scripts/generate_gemini_commands.py` (profile=full), `scripts/generate_gemini_skills.py` (profile=full) |
-| Tracked capabilities | `GEMINI.md`, `mcpServers`, tools, `settings.json`, `BeforeTool`, `AfterTool`, `BeforeToolSelection`, `BeforeAgent`, `AfterAgent`, `BeforeModel`, `AfterModel`, `Notification`, `PreCompress`, `SessionStart`, `SessionEnd`, `SKILL.md`, `activate_skill`, custom commands, `gemini-extension.json` (no native `Stop` event — generator maps Stop-equivalent to `AfterAgent`; 11 documented hook events total) |
+| Global install | `ai-toolkit install --editors gemini` writes `~/.gemini/GEMINI.md` **plus** hooks at `~/.gemini/settings.json` (profile ≥ standard) and `~/.gemini/commands/` + `~/.gemini/skills/` pointer (profile=full) — all documented user-tier surfaces. A global-only Gemini user previously got zero hooks. |
+| Tracked capabilities | `GEMINI.md`, `mcpServers`, tools, `settings.json`, `BeforeTool`, `AfterTool`, `BeforeToolSelection`, `BeforeAgent`, `AfterAgent`, `BeforeModel`, `AfterModel`, `Notification`, `PreCompress`, `SessionStart`, `SessionEnd`, `SKILL.md`, `activate_skill`, custom commands, `.gemini/agents/*.md` subagents, `gemini-extension.json` (no native `Stop` event — generator maps Stop-equivalent to `AfterAgent`; 11 documented hook events total) |
 | Version probe | `gemini --version` |
-| Latest upstream | v0.47.0 (2026-06-18). NOTE: Gemini CLI dropped free/paid individual tiers on 2026-06-18 in favor of Antigravity CLI (we ship `generate_antigravity.py`); enterprise Code Assist and paid API keys keep Gemini CLI, so the integration stays. The 11 hook events are unchanged. v0.48 preview migrates the `coreTools` setting to `tools.core` (a tool-allowlist key we do not emit, so no generator change). |
+| Latest upstream | v0.49.0 (2026-06-25; the stable line skipped v0.48.0 — its preview content was promoted into v0.49.0). NOTE: Gemini CLI dropped free/paid individual tiers on 2026-06-18 in favor of Antigravity CLI (we ship `generate_antigravity.py`); enterprise Code Assist and paid API keys keep Gemini CLI, so the integration stays. The 11 hook events are unchanged. v0.49.0 completed the `coreTools` → `tools.core` migration (auto-migrated; `tools.exclude` deprecated) — both are tool-allowlist keys we do not emit, so no generator change. Watch item: `.gemini/agents/*.md` / `~/.gemini/agents/*.md` native subagents are documented but we do not yet emit them (candidate `generate_gemini_agents.py`). |
 
 ### Cline
 
@@ -114,12 +136,12 @@ The canonical data lives in **`scripts/ecosystem_tools.json`** and is consumed b
 | Field | Value |
 |-------|-------|
 | ID | `roo-code` |
-| Docs | https://roocodeinc.github.io/Roo-Code (docs.roocode.com 301-redirects here) |
-| Release notes | https://github.com/RooCodeInc/Roo-Code/releases (**ARCHIVED** — repo read-only since 2026-05-15, frozen at v3.54.0; community fork reportedly continues) |
-| Config paths | `.roomodes`, `.roo/rules/*.md`, `.roo/rules-{slug}/*.md`, `.roo/mcp.json`, `~/.roo/rules/`, `~/.roo/custom_modes.yaml`, `mcp_settings.json` (global via Roo settings UI) |
+| Docs | https://roocodeinc.github.io/Roo-Code (frozen; docs.roocode.com 301-redirects here). Successor docs: https://docs.zoocode.dev |
+| Release notes | https://github.com/Zoo-Code-Org/Zoo-Code/releases (authoritative). **Original RooCodeInc/Roo-Code repo ARCHIVED/read-only since 2026-05-15, frozen at v3.54.0 — its feed is dead.** Successor project by former Roo contributors: **Zoo-Code-Org/Zoo-Code** (marketplace `ZooCodeOrganization.zoo-code`), active through v3.64.0 (2026-06-26). |
+| Config paths | `.roomodes` (JSON still fully supported), `.roo/rules/*.md`, `.roo/rules-{slug}/*.md`, `.roo/skills/*/SKILL.md`, `~/.roo/skills/*/SKILL.md`, `.agents/skills/*/SKILL.md`, `~/.agents/skills/*`, `.roo/commands/*.md`, `~/.roo/commands/*.md`, `.roo/mcp.json`, `~/.roo/rules/`, `mcp_settings.json` + global custom modes live in VS Code globalStorage (`<globalStorage>/rooveterinaryinc.roo-cline/settings/custom_modes.yaml`), NOT `~/.roo/custom_modes.yaml` |
 | Our generators | `scripts/generate_roo_modes.py`, `scripts/generate_roo_rules.py` |
-| Tracked capabilities | `roomodes`, custom modes, Code Actions, MCP, Orchestrator mode, `whenToUse`, `description`, `roleDefinition`, `groups` |
-| Notes | `.roomodes` now includes `description` and `whenToUse` for every mode (since 2026-04). YAML `.roomodes` is upstream-preferred but not yet emitted — JSON is still accepted by Roo. Global install writes only `~/.roo/rules/` because the exact global MCP settings path is UI-managed. |
+| Tracked capabilities | `roomodes`, custom modes, Code Actions, MCP, Orchestrator mode, `whenToUse`, `description`, `roleDefinition`, `groups`, skills, slash commands |
+| Notes | Config compat with the Zoo fork is total, so both generators stay valid unchanged. `.roomodes` includes `description`/`whenToUse` for every mode (since 2026-04); JSON is still accepted (YAML is upstream-preferred but not emitted). Global install writes `~/.roo/rules/` plus `~/.agents/skills/*` (Roo/Zoo native skill discovery, shipped v3.46.0/v3.47.2; skipped when `codex` is also selected). `~/.roo/commands/` (global slash commands, since v3.25) is a documented surface not yet generated. |
 
 ### Aider
 
@@ -144,7 +166,9 @@ The canonical data lives in **`scripts/ecosystem_tools.json`** and is consumed b
 | Changelog | https://www.augmentcode.com/changelog |
 | Config paths | `.augment/rules/*.md`, `.augment-guidelines` (workspace root, legacy single-file), `~/.augment/user-guidelines.md`, `.augment/agents/*.md`, `.augment/commands/*.md`, `.augment/skills/*/SKILL.md`, `.augment/settings.json`, `.augment/settings.local.json`, `~/.augment/rules/*.md`, `~/.augment/settings.json`, `/etc/augment/settings.json`. Auggie CLI also discovers skills/commands from `.claude/` and `.agents/` (`.augment/` wins on precedence). |
 | Our generators | `scripts/generate_augment.py`, `scripts/generate_augment_rules.py`, `scripts/generate_augment_agents.py` (profile=full), `scripts/generate_augment_commands.py` (profile=full), `scripts/generate_augment_hooks.py` (profile=full, HOME-scoped), `scripts/generate_augment_skills.py` (profile=full) |
-| Tracked capabilities | `.augment`, Agent mode, Next Edit, MCP, context engine, Auggie CLI, `always_apply`, `agent_requested`, subagents, custom commands, `SKILL.md`, `PreToolUse`, `PostToolUse`, `SessionStart`, `SessionEnd`, `Stop`, `Notification`, ACP Mode |
+| Global install | `ai-toolkit install --editors augment` writes `~/.augment/rules/ai-toolkit.md` **plus** (profile=full) `~/.augment/agents/`, `~/.augment/commands/`, and hooks in `~/.augment/settings.json` — all documented user-tier surfaces. A global-only Augment user previously got no hooks/agents/commands. Skills need no global emission: Auggie natively reads `~/.claude/skills/`. |
+| Tracked capabilities | `.augment`, Agent mode, Next Edit, MCP, context engine, Auggie CLI, `always_apply`, `agent_requested`, subagents, custom commands, `SKILL.md`, `PreToolUse`, `PostToolUse`, `SessionStart`, `SessionEnd`, `Stop`, `Notification`, ACP Mode, plugins/marketplace |
+| Latest / notes | Auggie CLI v0.31.0. Since v0.30.0 (2026-06-25) `PreToolUse`/`PostToolUse` hooks fire during sub-agent sessions, so our wired hook groups now run concurrently from parallel sub-agents — hook payload identifier is `conversation_id` (not `session_id`), a concurrency note to track. `Notification` is enum-only (doctor flipped its marker) — no dedicated handler documented, so class C (do NOT wire). Plugins/marketplace (`auggie plugin marketplace add`, `.augment-plugin`/`.claude-plugin` layouts, `enabledPlugins`/`autoUpdateMarketplaces` in settings) documented but not yet a shipping target. |
 | SPA caveat | Mintlify Next.js SPA; use `https://docs.augmentcode.com/<path>.md` siblings (discoverable via `/llms.txt`) for machine reads |
 
 ### Google Antigravity
@@ -155,9 +179,11 @@ The canonical data lives in **`scripts/ecosystem_tools.json`** and is consumed b
 | Docs | https://antigravity.google/docs (JavaScript SPA — use bundle strings / sitemap to verify) |
 | Changelog | https://antigravity.google/changelog (SPA; changelog entries embedded in main-*.js) |
 | Config paths | `.agents/rules/*.md`, `.agents/workflows/*.md` (plural is the Antigravity 2.0 default; singular `.agent/rules`, `.agent/workflows` still read as fallback), `.agent/skills/*/SKILL.md` (IDE), `.agents/skills/*/SKILL.md` (CLI), `.agents/hooks.json` (CLI hooks), `.agents/mcp_config.json` (CLI MCP), `AGENTS.md`, `GEMINI.md` |
-| Our generators | `scripts/generate_antigravity.py` (rules + workflows + skill pointer dual-emitted to `.agent/skills/` and `.agents/skills/`) |
-| Tracked capabilities | Antigravity, agent manager, artifacts, MCP, workflows, rules, skills, hooks, `AGENTS.md`, `GEMINI.md`, agent permissions |
-| CLI notes | Antigravity CLI (GA 2026-05-19): hooks in `.agents/hooks.json` use Claude-style event names (`PreToolUse`, not Gemini's `BeforeTool`) with a JSON stdin/stdout decision contract; MCP config `.agents/mcp_config.json` requires `serverUrl` (legacy `url`/`httpUrl` fail silently). Global MCP config path is inconsistently reported across sources (`~/.gemini/antigravity-cli/` vs `~/.gemini/config/`) — only the workspace path is registered until verified via `agy inspect`. |
+| Global config paths | Skills: `~/.gemini/config/skills/*/SKILL.md` (shared across all Antigravity products) and `~/.gemini/antigravity-cli/skills/*/SKILL.md` (CLI-private) — both documented in the official Skills codelab. MCP: `~/.gemini/config/mcp_config.json` (shared global, resolved by CLI v1.0.14; the `~/.gemini/antigravity-cli/mcp_config.json` path is legacy). Rules: `~/.gemini/GEMINI.md` (dual-owner with Gemini CLI — Antigravity's IDE "+ Global" writes the same file; gemini-cli#16058 closed "not planned"). Hooks: `~/.gemini/config/hooks.json` (shared, since CLI v1.0.8). |
+| Our generators | `scripts/generate_antigravity.py` (rules + workflows + skill pointer dual-emitted to `.agent/skills/` and `.agents/skills/`; `generate_global()` writes the pointer to the two HOME skill dirs) |
+| Global install | `ai-toolkit install --editors antigravity` writes the skill pointer to `~/.gemini/config/skills/` and `~/.gemini/antigravity-cli/skills/`. Rules stay project-local (no mergeable global rules file beyond the Gemini-CLI-shared `~/.gemini/GEMINI.md`, covered by `--editors gemini`). |
+| Tracked capabilities | Antigravity, agent manager, artifacts, MCP, workflows, rules, skills, hooks, `AGENTS.md`, `GEMINI.md`, agent permissions, global skills, `~/.gemini/config/mcp_config.json` |
+| CLI notes | Antigravity CLI (GA 2026-05-19; latest CLI v1.0.14 2026-06-30, IDE 2.2.1). Hooks are IDE + CLI (`.agents/hooks.json` workspace, `~/.gemini/config/hooks.json` global; event set `PreToolUse`/`PostToolUse`/`PreInvocation`/`PostInvocation`/`Stop` — `PreInvocation`/`PostInvocation` have no Claude equivalent; shell tool is `run_command` with args at `.toolCall.args.CommandLine`). MCP: `url` is natively supported since CLI v1.0.5 (registry's old "url/httpUrl fail silently" note is stale); `serverUrl` works everywhere incl. IDE. **MCP adapter + a `generate_antigravity_hooks.py` are not yet shipped** (backlog). |
 | Doc access note | Docs are JS-SPA — verify via `main-*.js` bundle strings or community skill repos. `WebFetch` returns an empty shell. The sitemap.xml is stale (omits the `cli-*` doc pages), so sitemap-based monitoring misses CLI doc additions. |
 
 ### Codex CLI
@@ -165,13 +191,13 @@ The canonical data lives in **`scripts/ecosystem_tools.json`** and is consumed b
 | Field | Value |
 |-------|-------|
 | ID | `codex-cli` |
-| Docs | https://developers.openai.com/codex (live docs site; config pages split into `/codex/config-basic`, `/codex/config-reference`, `/codex/config-advanced` plus `/codex/hooks`, `/codex/skills`; latest stable codex-cli 0.142.0, 2026-06) |
+| Docs | https://developers.openai.com/codex (live docs site; config pages split into `/codex/config-basic`, `/codex/config-reference`, `/codex/config-advanced` plus `/codex/hooks`, `/codex/skills`, `/codex/guides/agents-md`; latest verified local/release: codex-cli 0.144.1, 2026-07-10) |
 | Release notes | https://github.com/openai/codex/releases |
-| Config paths | `AGENTS.md`, `.agents/skills/*/SKILL.md`, `.codex/hooks.json`, `.codex/config.toml` (project layers, root→cwd, closest wins, trusted projects only), `~/.codex/config.toml` |
+| Config paths | **Instructions:** project `AGENTS.md` (root→cwd chain, closest wins) and global `~/.codex/AGENTS.md` (`$CODEX_HOME/AGENTS.md`; `~/.codex/AGENTS.override.md` takes precedence). NOTE: `~/AGENTS.md` is NOT a global-instruction surface — Codex only reads it if a session's cwd is exactly `$HOME`. Plus `.agents/skills/*/SKILL.md`, `.codex/hooks.json`, `~/.codex/hooks.json`, `.codex/config.toml` (project layers, root→cwd, closest wins, trusted projects only), `~/.codex/config.toml`. |
 | Our generators | `scripts/generate_codex.py`, `scripts/generate_codex_hooks.py`, `scripts/generate_codex_skills.py` (opt-in via `--codex-skills`) |
-| Rules delivery | Universal coding rules are inlined into `AGENTS.md` (Codex reads instructions only from AGENTS.md, not `.agents/rules/`); language rules ship as `<lang>-rules` skills under `.agents/skills/`. |
-| Tracked hook events | Upstream canonical (codex-rs `HookEventName` enum): `PreToolUse`, `PostToolUse`, `PermissionRequest`, `PreCompact`, `PostCompact`, `SessionStart`, `UserPromptSubmit`, `SubagentStart`, `SubagentStop`, `Stop` (10 events). We wire 9 of these to shared toolkit hook scripts, mirroring the Claude Code mapping in `app/hooks.json`. `PostCompact` is not wired (its only hook was the removed environment-snapshot probe). |
-| Tracked handler types | `command` (emitted by default); `prompt` and `agent` available upstream but authored by hand |
+| Rules delivery | Universal coding rules are inlined into `AGENTS.md` (Codex reads instructions only from AGENTS.md, not `.agents/rules/`); language rules ship as `<lang>-rules` skills under `.agents/skills/`. Global install writes `~/.codex/AGENTS.md` (not `~/AGENTS.md`, which Codex never loads globally); plugin-pack rules are marker-injected into the same file. `project_doc_max_bytes` default is 32 KiB and Codex silently truncates AGENTS.md past that (see codex-cli-compatibility.md). |
+| Tracked hook events | Upstream canonical (codex-rs `HookEventName` enum): `PreToolUse`, `PostToolUse`, `PermissionRequest`, `PreCompact`, `PostCompact`, `SessionStart`, `UserPromptSubmit`, `SubagentStart`, `SubagentStop`, `Stop` (10 events). We wire 9 of these to shared toolkit hook scripts (via `generate_codex_hooks.py` AND `inject-hook` propagation, kept in sync), mirroring the Claude Code mapping in `app/hooks.json`. `PostCompact` is not wired (its only hook was the removed environment-snapshot probe). |
+| Tracked handler types | `command` (emitted by default; the only handler Codex actually runs). `prompt` and `agent` are parsed by Codex but NOT yet executed, so hand-authored handlers of those types are inert. |
 | Other capabilities | `AGENTS.md`, `config.toml`, `mcp_servers`, sandbox policies, `.agents/skills/*/SKILL.md` (native Codex skill discovery path) |
 | Version probe | `codex --version` |
 

package/kb/reference/unique-features.md

@@ -4,7 +4,7 @@ category: reference
 service: ai-toolkit
 tags: [features, differentiators, constitution, hooks, security, tdd, memory]
 created: "2026-04-13"
-last_updated: "2026-05-12"
+last_updated: "2026-07-10"
 description: "Detailed description of ai-toolkit's unique features: constitution enforcement, hooks system, security scanning, effort budgeting, quality gates, and more."
 ---
 
@@ -12,7 +12,7 @@ description: "Detailed description of ai-toolkit's unique features: constitution
 
 ## 1. Machine-Enforced Constitution
 
-Unlike other toolkits that put safety rules in documentation only, ai-toolkit enforces a 6-article constitution via hooks. The hooks actually **block** execution of:
+Unlike other toolkits that put safety rules in documentation only, ai-toolkit enforces a 7-article constitution via hooks. The hooks actually **block** execution of:
 - Mass deletion (`rm -rf`, `DROP TABLE`)
 - Blind overwrites of uncommitted work
 - Any action that could cause irreversible data loss
@@ -37,6 +37,7 @@ Hook logic lives in `app/hooks/*.sh` — not inline JSON one-liners. Scripts are
 | UserPromptSubmit | `track-usage.sh` | Record skill invocations to local stats |
 | PostToolUse | `post-tool-use.sh` | Lightweight validation reminders + append edit to session state |
 | PostToolUse | `governance-capture.sh` | Log security-sensitive operations to JSONL |
+| PostToolUse | `loop-guard.sh` | Detect repeated successful actions and inject a reassessment advisory |
 | PostToolUse | `test-cohesion.sh` | Run cohesion-mapped tests after edits; block on failure (Art. VI.3) |
 | PostToolUse | `search-tracker.sh` | Clear search-first flag when smart_query/hybrid_search_kb/Web* runs |
 | Stop | `quality-check.sh` | Multi-language lint (ruff/tsc/phpstan/dart/go) |