@softspark/ai-toolkit 4.24.1 → 4.25.1

package/CHANGELOG.md

@@ -7,6 +7,69 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 
 ---
 
+## v4.25.1 — npm advisories count again (2026-08-19)
+
+### Fixed
+
+- **`cve-scan` reported zero findings for a vulnerable npm project.** npm audit
+  can return the legacy `advisories` object as well as the current
+  `vulnerabilities` object. The scanner parsed only the latter, so five real
+  lodash advisories remained trapped in `raw_output` while `total_findings` was
+  zero and the process exited successfully. Both formats are now normalized,
+  and HIGH advisories restore the documented non-zero exit code.
+
+### Changed
+
+- **The published-package scanner smoke uses real per-scanner fixtures and
+  flags.** It now includes healthcare patterns and a deliberately vulnerable
+  locked npm dependency, invokes `cve-scan` with `--json`, and treats raw npm
+  advisories with no normalized findings as a parser failure.
+
+### Tests
+
+- Added a public-CLI regression test with a stubbed legacy npm audit response;
+  it asserts normalized severity, installed version, CVE, fixed range, finding
+  count, and exit status.
+
+## v4.25.0 — editor-native integrations catch up (2026-08-19)
+
+### Added
+
+- **Codex now has an exact native hook and plugin contract.** The hook generator
+  covers all 11 supported events, including bounded `SessionEnd`, while the new
+  deterministic plugin exporter bundles required runtime resources and verifies
+  the complete archive offline before installation.
+- **Google Antigravity gains native hooks, agents, plugin packaging, MCP mapping,
+  and install profiles.** Generated hooks use the documented five-event schema;
+  project and user installs use the current IDE and CLI paths without conflating
+  legacy compatibility surfaces.
+- **Gemini, OpenCode, and Cline gain native assets.** Gemini receives local agent
+  files, OpenCode receives complete native skill directories, and Cline receives
+  native rules plus all eight current extension and CLI hook events.
+
+### Changed
+
+- **Claude Code validation follows the current hook and plugin schemas.** Prompt
+  and agent handlers share the documented 13-event allowlist, HTTP handlers are
+  restricted to their supported lifecycle, and current plugin surfaces include
+  workflows, output styles, and themes.
+- **Editor installation and removal are transactional.** Profile downgrades and
+  uninstall remove only toolkit-managed assets, preserve user files, and cover
+  the new native Gemini, OpenCode, Antigravity, and Cline paths.
+
+### Security
+
+- **Filesystem writers reject symlink ancestry and ancestor-swap attacks.** New
+  generators and cleanup paths use pinned transactions with rollback, while
+  plugin verification rejects missing, extra, modified, or wrongly-modeled
+  archive members.
+
+### Ecosystem
+
+- Refreshed the 13-tool compatibility registry and upstream snapshot after
+  revalidating Claude Code, Codex CLI, Antigravity, Gemini, OpenCode, and Cline
+  against their current native contracts.
+
 ## v4.24.1 — a dead link reported itself as installed (2026-08-19)
 
 ### Fixed

package/README.md

@@ -6,17 +6,18 @@
 [![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
 [![Skills](https://img.shields.io/badge/skills-109-brightgreen)](app/skills/)
 [![Agents](https://img.shields.io/badge/agents-44-blue)](app/agents/)
-[![Tests](https://img.shields.io/badge/tests-1524%20passing-success)](tests/)
+[![Tests](https://img.shields.io/badge/tests-1637%20passing-success)](tests/)
 
-## What's New in v4.24.1
+## What's New in v4.25.1
 
-**v4.24.1** — `plugin install` accepted a dead symlink as proof of installation.
-The guard asked `exists() or is_symlink()`, and a link with no target still
-answers yes to the second half, so the installer logged `OK` and repaired
-nothing — precisely the state a toolkit upgrade leaves, since replacing `app/`
-breaks every link into it. Dangling links are now dropped and relinked; real
-files and live links stay untouched. Pairs with v4.24.0's user-level pack root,
-which is what stops the breakage happening in the first place.
+**v4.25.1** fixes the CVE scanner path exercised by the published-package smoke test:
+
+- Legacy npm audit `advisories` are normalized alongside the modern
+  `vulnerabilities` response.
+- HIGH advisories now produce findings and the documented non-zero exit code
+  instead of a false clean result.
+- The post-release scanner fixture now exercises accessibility, SEO, HIPAA, and
+  a deliberately vulnerable npm dependency with their real CLI flags.
 
 See [CHANGELOG.md](CHANGELOG.md) for full history.
 
@@ -91,6 +92,24 @@ ai-toolkit claude-app export --verify
 Re-export and re-upload after toolkit or registered-rule updates. Skills work
 in Chat and Cowork; hooks and sub-agents are active only in Cowork.
 
+### Native Codex Plugin
+
+Build or validate the marketplace-ready Codex package without changing
+`~/.agents` or `~/.codex`:
+
+```bash
+ai-toolkit codex-plugin export --output ai-toolkit-codex-plugin.zip
+ai-toolkit codex-plugin verify
+```
+
+Extract the ZIP into a local marketplace under `plugins/ai-toolkit/`, add that
+marketplace with `codex plugin marketplace add <marketplace-root>`, then install
+from `/plugins` in Codex CLI and start a new session. Review and trust the
+bundled hooks before use. The ZIP includes plugin-local persona definitions,
+the briefing helper, the skill-audit helper and its local imports, and other
+referenced skill resources. Export rejects symlinked output paths and ancestors.
+Codex IDE does not support plugins.
+
 ### Install Profiles
 
 ```bash
@@ -118,15 +137,15 @@ See [CLI Reference](kb/reference/cli-reference.md) for all commands and options.
 | Claude Chat / Cowork | uploaded plugin ZIP + UI global/folder instructions | Cowork only | account/app |
 | Cursor | `.cursor/rules/*.mdc` + `.cursor/mcp.json` + `.cursor/skills/*` | ✅ | project (`~/.cursor/mcp.json` for MCP only) |
 | Windsurf (Devin Desktop) | `~/.config/devin/AGENTS.md` + `.devin/rules/*.md` + `.devin/hooks.v1.json` + `.windsurf/skills/*` | ✅ | global + project |
-| Gemini CLI | `~/.gemini/GEMINI.md` | ✅ | global |
+| Gemini CLI | `~/.gemini/GEMINI.md` + `.gemini/settings.json` + `.gemini/{commands,skills,agents}/` | ✅ | project + user |
 | GitHub Copilot | Project: `AGENTS.md` + `.github/copilot-instructions.md` + `.github/{instructions,prompts,agents,skills,hooks}/` + `.github/mcp.json`; user: `$COPILOT_HOME/copilot-instructions.md` + `$COPILOT_HOME/{instructions,agents,skills,hooks}/` + `$COPILOT_HOME/mcp-config.json` | ✅ | project + user |
-| Cline | `~/Documents/Cline/Rules/*.md` + `~/.cline/skills/*` + `.clinerules/*.md` | — | global + project |
+| Cline | Project: `.cline/{rules,hooks,skills}/` + `.clinerules/{hooks,workflows}/`; user: `~/.cline/{rules,hooks,skills}/` + `~/Documents/Cline/{Rules,Hooks}/` compatibility | ✅ | global + project |
 | Roo Code / [Zoo Code](https://zoocode.dev/) | `~/.roo/rules/*.md` + `.roomodes` + `.roo/rules/*.md` | — | global rules + project |
 | Aider | `~/.aider.conf.yml` + `.aider.conf.yml` + `CONVENTIONS.md` | — | global + project |
 | Augment | `~/.augment/rules/*.md` + `.augment/rules/ai-toolkit-*.md` | ✅ | global + project |
-| Google Antigravity | `.agents/rules/*.md` + `.agents/workflows/*.md` + skill pointer in `.agent/skills/*` (IDE) and `.agents/skills/*` (CLI) | — | project |
+| Google Antigravity | Project `.agents/{rules,workflows,skills,agents,hooks}/`; user `~/.gemini/config/{skills,agents,hooks}/`; opt-in native plugin export | ✅ | project + user |
 | Codex CLI | Project: `AGENTS.md` + `.agents/skills/*` + `.codex/{agents,hooks}/` + `.codex/{hooks.json,config.toml}`; user: `$CODEX_HOME/{AGENTS.md,agents,hooks.json,config.toml}` + `$HOME/.agents/skills/*` | ✅ | project + user |
-| opencode | `AGENTS.md` + `.opencode/{agents,commands,plugins}/*` + `opencode.json` | ✅ | project + global (`~/.config/opencode/`) |
+| opencode | `AGENTS.md` + `.opencode/{agents,commands,plugins,skills}/*` + `opencode.{json,jsonc}` | ✅ | project + global (`~/.config/opencode/`) |
 
 > Claude Code is always installed (primary platform). Other editors are selected with `--editors`; the Claude app uses the separate `claude-app export` flow because its customization store is UI/plugin-managed. The **Hooks** column marks platforms with lifecycle enforcement. Platforms marked — receive guidance without blocking hooks.
 
@@ -164,7 +183,7 @@ ai-toolkit/
 │   └── ARCHITECTURE.md  # Full system design
 ├── kb/                  # Reference docs, procedures, plans
 ├── scripts/             # Validation, install, evaluation scripts
-├── tests/               # Bats and Python test suite (1494 tests)
+├── tests/               # Bats and Python test suite (1637 tests)
 └── CHANGELOG.md
 ```
 

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

@@ -3,7 +3,7 @@
   "name": "ai-toolkit",
   "displayName": "AI Toolkit",
   "description": "Professional-grade engineering skills, agents, rules, and lifecycle guardrails for Claude Code, Claude Chat, and Cowork.",
-  "version": "4.24.1",
+  "version": "4.25.1",
   "author": {
     "name": "SoftSpark",
     "url": "https://github.com/softspark"

package/app/skills/cve-scan/scripts/cve_scan.py

@@ -9,7 +9,6 @@ Stdlib only. No external dependencies.
 """
 
 import json
-import os
 import shutil
 import subprocess
 import sys
@@ -141,7 +140,7 @@ def run_audit(eco: dict, root: Path, fix: bool = False) -> dict:
     except FileNotFoundError:
         result["error"] = f"Tool '{eco['tool']}' not found in PATH"
     except subprocess.TimeoutExpired:
-        result["error"] = f"Audit command timed out after 120s"
+        result["error"] = "Audit command timed out after 120s"
 
     return result
 
@@ -168,6 +167,21 @@ def parse_npm_audit(raw: str) -> list[dict]:
                     "url": via.get("url", ""),
                     "fixed_in": info.get("fixAvailable", {}).get("version", "unknown") if isinstance(info.get("fixAvailable"), dict) else "unknown",
                 })
+
+    for advisory in data.get("advisories", {}).values():
+        installed_versions = sorted({
+            finding.get("version", "unknown")
+            for finding in advisory.get("findings", [])
+        })
+        findings.append({
+            "severity": advisory.get("severity", "unknown").upper(),
+            "package": advisory.get("module_name", "unknown"),
+            "installed": ", ".join(installed_versions) or "unknown",
+            "cve": advisory.get("cves", []) or [advisory.get("github_advisory_id", "N/A")],
+            "title": advisory.get("title", "Unknown"),
+            "url": advisory.get("url", ""),
+            "fixed_in": advisory.get("patched_versions", "unknown"),
+        })
     return findings
 
 

package/app/skills/hook-creator/SKILL.md

@@ -23,7 +23,7 @@ Create a new Claude Code hook following ai-toolkit conventions.
 | `SessionEnd` | Session is closing | any | Flush logs, save transcripts |
 | `UserPromptSubmit` | User submits a prompt | any | Prompt governance, usage tracking |
 | `Notification` | Claude sends a notification | any | OS alerts, Slack pings |
-| `MessageDisplay` | Assistant message is about to be shown to the user | any | Transform or hide assistant message text before display |
+| `MessageDisplay` | Assistant message text streams in completed-line batches | none | Return `displayContent` to replace the rendered batch without changing the transcript |
 
 ### Tool lifecycle
 
@@ -80,6 +80,7 @@ Create a new Claude Code hook following ai-toolkit conventions.
 | `WorktreeCreate` | Worktree is being created; `type: "http"` can return `hookSpecificOutput.worktreePath` | any | Provision worktree dirs |
 | `WorktreeRemove` | Worktree is being removed | any | Cleanup |
 | `CwdChanged` | Working directory changes during a session | any | Reactive env management (e.g., direnv) |
+| `DirectoryAdded` | A working directory was added with `/add-dir` or SDK `register_repo_root`; runs asynchronously after the add and cannot block it | `slash_command\|register_repo_root` | Prepare a newly added repository |
 | `FileChanged` | Tracked file is modified on disk | any | Re-lint, reload config |
 | `ConfigChange` | Settings / config file changed | any | Re-validate, warn on drift |
 
@@ -99,7 +100,7 @@ Claude Code supports five handler `type` values in `hooks.json`:
 | `command` | Run a shell script / binary | `command` (path + args) |
 | `http` | Call a local or remote HTTP endpoint | `url` |
 | `prompt` | Inject a prompt to the fast inline model and use its verdict | `prompt` |
-| `agent` | Spawn a full subagent to evaluate the event (must target `Stop` / `SubagentStop`) | `agent` (agent name) |
+| `agent` | Spawn an experimental tool-using subagent to evaluate the event | `prompt` |
 | `mcp_tool` | Invoke an MCP tool directly (no subprocess) | `server`, `tool`, `arguments` |
 
 `command` remains the default and ai-toolkit's hook entries all use it. The other types are documented here so you can author them by hand when needed.
@@ -146,9 +147,22 @@ Required fields:
 - `hooks[].command`: path to script using `$HOME/.softspark/ai-toolkit/hooks/` prefix (for `type: command`)
 
 Optional fields (read from Claude Code docs, not emitted by ai-toolkit by default):
-- `hooks[].timeout`: seconds to wait before killing the hook (global default applies if omitted)
-- `hooks[].if`: permission-rule filter (e.g. `"Bash(git push*)"`) to reduce process spawning
+
+Common to every handler type:
+- `hooks[].if`: one permission-rule filter (e.g. `"Bash(git push*)"`); evaluated only for tool events
+- `hooks[].timeout`: seconds to wait before canceling the handler (type and event defaults apply if omitted)
 - `hooks[].statusMessage`: short message surfaced in the UI while the hook runs
+- `hooks[].once`: run once per session; only honored in skill frontmatter and ignored in settings files or agent frontmatter
+
+Command-handler fields:
+- `hooks[].args`: argument vector for exec form. Prefer exec form when a command uses `${CLAUDE_PROJECT_DIR}`, `${CLAUDE_PLUGIN_ROOT}`, or `${CLAUDE_PLUGIN_DATA}` path placeholders
+- `hooks[].async`: run in the background without blocking; background hooks cannot return decisions
+- `hooks[].asyncRewake`: run in the background and wake Claude on exit code 2; implies `async`
+- `hooks[].shell`: choose `bash` or `powershell` for shell form; ignored when `args` selects exec form
+
+Prompt and agent handlers both require `hooks[].prompt`; `type: agent` does not accept an agent name field. Agent handlers are experimental, so prefer `command` for production enforcement.
+
+`MessageDisplay` has no matcher, runs once per rendered batch in interactive sessions, and defaults to a 10-second timeout. Its `displayContent` output changes only the screen text; Claude and the transcript retain the original response. `DirectoryAdded` is always asynchronous and non-blocking regardless of the handler configuration.
 
 ## Script Template
 

package/app/surface.json

@@ -244,6 +244,7 @@
     "add-rule",
     "agents-md",
     "aider-conf",
+    "antigravity-plugin",
     "antigravity-rules",
     "augment-dir-rules",
     "augment-rules",
@@ -251,9 +252,11 @@
     "benchmark-ecosystem",
     "claude-app",
     "cline-dir-rules",
+    "cline-hooks",
     "cline-rules",
     "codex-hooks",
     "codex-md",
+    "codex-plugin",
     "compile-slm",
     "config",
     "conventions-md",
@@ -277,6 +280,7 @@
     "opencode-json",
     "opencode-md",
     "opencode-plugin",
+    "opencode-skills",
     "pack-codebase",
     "plugin",
     "projects",

package/benchmarks/ecosystem-doctor-snapshot.json

@@ -1,5 +1,5 @@
 {
-  "last_run": "2026-08-06T05:13:55Z",
+  "last_run": "2026-08-19T14:01:09Z",
   "schema_version": 1,
   "tools": {
     "aider": {
@@ -24,7 +24,7 @@
       }
     },
     "augment": {
-      "docs_hash": "68eecb3b6a49f7f1",
+      "docs_hash": "0f7df1fdf4962938",
       "headings": [
         "Admin",
         "Auggie CLI",
@@ -66,7 +66,7 @@
       }
     },
     "claude-app": {
-      "docs_hash": "670f833a8e1527c0",
+      "docs_hash": "5bba2a625b109b69",
       "headings": [
         "Add global and folder instructions",
         "Availability",
@@ -84,11 +84,11 @@
         "Get started with Claude Cowork",
         "Global instructions",
         "How Claude Cowork runs your tasks",
-        "I don't see Cowork on web or mobile",
         "I'm hitting usage limits quickly",
         "I'm seeing "Setting up Claude's workspace" when I start Cowork; what does this mean?",
         "Key capabilities",
         "Permissions and security",
+        "Related Articles",
         "Requirements",
         "Research and analysis",
         "Schedule recurring tasks",
@@ -107,7 +107,7 @@
       }
     },
     "claude-code": {
-      "docs_hash": "1904e0148fe997b9",
+      "docs_hash": "3d4394d0bf5dd8c1",
       "headings": [
         "Core concepts",
         "Documentation Index",
@@ -124,10 +124,12 @@
       "markers": {
         "ConfigChange": false,
         "CwdChanged": false,
+        "DirectoryAdded": false,
         "Elicitation": false,
         "ElicitationResult": false,
         "FileChanged": false,
         "InstructionsLoaded": false,
+        "LSP servers": false,
         "MCP server": true,
         "MessageDisplay": false,
         "Notification": false,
@@ -154,19 +156,27 @@
         "UserPromptSubmit": false,
         "WorktreeCreate": false,
         "WorktreeRemove": false,
+        "channels": true,
         "hook handler: agent": false,
         "hook handler: command": false,
         "hook handler: http": false,
         "hook handler: mcp_tool": false,
         "hook handler: prompt": false,
+        "monitors": false,
         "output style": false,
+        "outputStyles": false,
+        "plugins": true,
+        "settings.json": true,
         "slash command": false,
-        "sub-agent": true
+        "sub-agent": true,
+        "themes": true,
+        "userConfig": false,
+        "workflows": true
       },
-      "version": "2.1.223 (Claude Code)"
+      "version": "2.1.235 (Claude Code)"
     },
     "cline": {
-      "docs_hash": "e4409c39f56583e8",
+      "docs_hash": "bf058b01d03e0455",
       "headings": [
         "API Reference",
         "Best Practices",
@@ -213,7 +223,7 @@
       }
     },
     "codex-cli": {
-      "docs_hash": "91d1d7112da069da",
+      "docs_hash": "61aea7a06c8c6355",
       "headings": [
         "API",
         "API Reference",
@@ -247,6 +257,7 @@
         "Core concepts",
         "Cost and throughput",
         "Customization",
+        "Cyber safety",
         "Deployment and model providers",
         "Desktop app",
         "Development workflows",
@@ -272,6 +283,7 @@
         "Install Codex",
         "Keep the coding loop in your terminal",
         "Legacy APIs",
+        "Linux",
         "Measurement",
         "Media",
         "Move work to Codex cloud",
@@ -293,7 +305,6 @@
         "Review changes before they ship",
         "Run Codex and sign in",
         "SDKs and CLI",
-        "Safety",
         "Safety and governance",
         "Search and retrieval",
         "Search for current context",
@@ -325,14 +336,18 @@
       ],
       "markers": {
         ".agents/skills": false,
+        ".codex-plugin/plugin.json": false,
         ".codex/agents": false,
+        "/plugins": true,
         "AGENTS.md": true,
+        "PLUGIN_ROOT": false,
         "config.toml": false,
         "hook event: PermissionRequest": false,
         "hook event: PostCompact": false,
         "hook event: PostToolUse": false,
         "hook event: PreCompact": false,
         "hook event: PreToolUse": false,
+        "hook event: SessionEnd": false,
         "hook event: SessionStart": false,
         "hook event: Stop": false,
         "hook event: SubagentStart": false,
@@ -342,14 +357,32 @@
         "hook handler: command": false,
         "hook handler: prompt": false,
         "hooks": true,
+        "hooks/hooks.json": false,
         "mcp_servers": false,
+        "plugin marketplace": false,
         "sandbox": true
       },
-      "version": "codex-cli 0.146.0"
+      "version": "codex-cli 0.147.0"
     },
     "cursor": {
-      "docs_hash": "9d032d0dae73bed2",
-      "headings": [],
+      "docs_hash": "793ca4e25e676e17",
+      "headings": [
+        "Agent",
+        "CLI",
+        "Cloud Agents",
+        "Command Palette",
+        "Cursor Documentation",
+        "Customize",
+        "Get Started",
+        "Integrations",
+        "Models",
+        "More resources",
+        "Origin",
+        "SDK",
+        "Start here",
+        "Teams & Enterprise",
+        "What you can do with Cursor"
+      ],
       "markers": {
         ".cursor/rules": false,
         "AGENTS.md": false,
@@ -364,7 +397,7 @@
       }
     },
     "gemini-cli": {
-      "docs_hash": "d47d074674e59f6f",
+      "docs_hash": "f343c5f7c60fefcf",
       "headings": [
         "Breadcrumbs",
         "Directory actions",
@@ -381,6 +414,7 @@
         "parent directory"
       ],
       "markers": {
+        ".gemini/agents/*.md": false,
         "AfterAgent": false,
         "AfterModel": false,
         "AfterTool": false,
@@ -400,10 +434,11 @@
         "mcpServers": false,
         "settings.json": false,
         "tools": true
-      }
+      },
+      "version": "0.55.1"
     },
     "github-copilot": {
-      "docs_hash": "ee88f952816a8535",
+      "docs_hash": "79d741f4e3273f8d",
       "headings": [
         "About Copilot auto model selection",
         "About Copilot automations",
@@ -440,23 +475,34 @@
       }
     },
     "google-antigravity": {
-      "docs_hash": "1e0c0d249231d2a9",
+      "docs_hash": "8cbf9aaffb6b57bf",
       "headings": [],
       "markers": {
         "AGENTS.md": false,
         "GEMINI.md": false,
         "MCP": false,
+        "PostInvocation": false,
+        "PostToolUse": false,
+        "PreInvocation": false,
+        "PreToolUse": false,
+        "Stop": false,
         "agent manager": false,
         "agent permissions": false,
         "artifacts": false,
+        "global agents": false,
+        "global hooks": false,
+        "global skills": false,
         "hooks": false,
+        "plugins": false,
         "rules": false,
+        "serverUrl": false,
         "skills": false,
+        "subagents": false,
         "workflows": false
       }
     },
     "opencode": {
-      "docs_hash": "f09f3fbe98570961",
+      "docs_hash": "b112229db465d2e4",
       "headings": [
         "Add features",
         "Ask questions",
@@ -479,6 +525,7 @@
         "opencode.json": false,
         "permission.skill": false,
         "plugin event: command.executed": false,
+        "plugin event: message.part.updated": false,
         "plugin event: message.updated": false,
         "plugin event: permission.asked": false,
         "plugin event: session.compacted": false,
@@ -491,6 +538,7 @@
         "rules": true,
         "skills (native .opencode/skills)": false,
         "skills (via .claude/skills fallback)": false,
+        "skills array (local paths + HTTP URLs)": false,
         "subagent mode": false
       }
     },
@@ -516,7 +564,7 @@
       }
     },
     "windsurf": {
-      "docs_hash": "496619fda7ca4576",
+      "docs_hash": "fddce54b82ac479e",
       "headings": [
         "Accounts",
         "Advanced",

package/bin/ai-toolkit.js

@@ -57,6 +57,8 @@ const SCRIPT_COMMANDS = {
   'compile-slm':          { script: 'compile_slm.py' },
   'pack-codebase':        { script: 'pack_codebase.py' },
   'claude-app':           { script: 'claude_app.py',          toolkitCwd: true },
+  'codex-plugin':         { script: 'codex_plugin.py',         toolkitCwd: true },
+  'antigravity-plugin':   { script: 'antigravity_plugin.py',   toolkitCwd: true },
 };
 
 // ---------------------------------------------------------------------------
@@ -96,7 +98,8 @@ const COMMANDS = {
   'copilot-instructions': 'Generate .github/copilot-instructions.md',
   'gemini-md': 'Generate GEMINI.md for Gemini CLI',
   'cline-rules': 'Generate .clinerules for Cline (legacy)',
-  'cline-dir-rules': 'Generate .clinerules/*.md for Cline (recommended)',
+  'cline-dir-rules': 'Generate .cline/rules/*.md plus .clinerules/*.md compatibility for Cline',
+  'cline-hooks': 'Generate .cline/hooks/<Event> plus .clinerules/hooks/<Event> compatibility',
   'roo-modes': 'Generate .roomodes for Roo Code',
   'roo-dir-rules': 'Generate .roo/rules/*.md shared rules for Roo Code',
   'aider-conf': 'Generate .aider.conf.yml for Aider',
@@ -109,12 +112,15 @@ const COMMANDS = {
   'opencode-md': 'Generate AGENTS.md for opencode',
   'opencode-agents': 'Generate .opencode/agents/ for opencode (subagents)',
   'opencode-commands': 'Generate .opencode/commands/ for opencode (slash commands)',
+  'opencode-skills': 'Generate .opencode/skills/ for opencode (Agent Skills)',
   'opencode-plugin': 'Generate .opencode/plugins/ai-toolkit-hooks.js (lifecycle bridge)',
   'opencode-json': 'Merge .mcp.json servers into opencode.json',
   'agents-md': 'Regenerate AGENTS.md from agent definitions',
   'compile-slm': 'Compile toolkit into a minimal SLM system prompt (--budget, --model-size, --dry-run)',
   'pack-codebase': 'Pack the current codebase into a single AI-friendly markdown file (--budget, --include, --exclude, --dry-run)',
   'claude-app': 'Export or verify the uploadable Claude Chat/Desktop/Cowork plugin',
+  'codex-plugin': 'Export or verify the native Codex CLI plugin package',
+  'antigravity-plugin': 'Export or verify the native Google Antigravity plugin package',
   'llms-txt': 'Generate llms.txt and llms-full.txt',
   'generate-all': 'Generate all platform configs at once (agents, cursor, windsurf, copilot, gemini, cline, roo, aider, augment, antigravity, codex, opencode, llms)',
   help: 'Show this help message',
@@ -290,6 +296,17 @@ function showHelp() {
   console.log('  export [--output FILE] [--no-custom-rules] [--verify]');
   console.log('                  Build a ZIP for Customize > Plugins and Cowork instructions');
   console.log('  verify          Run structural checks and the official Claude plugin validator');
+  console.log('\nOptions for codex-plugin:');
+  console.log('  export [--output FILE]  Build a deterministic native Codex plugin ZIP');
+  console.log('  verify          Validate structure, schema, paths, hooks, and self-containment');
+  console.log('                  Install/use through a local marketplace and /plugins in Codex CLI');
+  console.log('                  Codex IDE does not support plugins');
+  console.log('\nOptions for antigravity-plugin:');
+  console.log('  export [output|--output FILE]  Build a deterministic Antigravity plugin ZIP');
+  console.log('  verify <archive-or-dir>        Validate schema, paths, hooks, and self-containment');
+  console.log('                  Install under .agents/plugins/<name>/ (workspace),');
+  console.log('                  ~/.gemini/antigravity-cli/plugins/<name>/ (CLI), or');
+  console.log('                  ~/.gemini/config/plugins/<name>/ (IDE/shared product)');
   console.log('\nOptions for mcp:');
   console.log('  list                          List available MCP templates');
   console.log('  editors                       List editors with native MCP config adapters');
@@ -502,20 +519,25 @@ function handleGenerateAll(_args) {
   for (const [name, gen] of Object.entries(GENERATORS)) {
     // Skip codex-md and opencode-md — they inject into AGENTS.md via markers
     // (used by install --local --editors codex|opencode), not as standalone files.
-    // agents-md generates the full agent list which is the standalone AGENTS.md.
-    if (name === 'codex-md' || name === 'opencode-md') continue;
+    // The native Cline generator below emits both current and compatibility rules;
+    // generating the retired single-file surface first would block that directory.
+    if (name === 'codex-md' || name === 'opencode-md' || name === 'cline-rules') continue;
     writeGeneratorOutput(gen);
   }
   // Directory-based generators (multi-file output)
   run(scriptPath('generate_antigravity.py'), [CWD]);
+  run(scriptPath('generate_antigravity_hooks.py'), [CWD]);
+  run(scriptPath('generate_antigravity_agents.py'), [CWD]);
   run(scriptPath('generate_cursor_mdc.py'), [CWD]);
   run(scriptPath('generate_windsurf_rules.py'), [CWD]);
   run(scriptPath('generate_cline_rules.py'), [CWD]);
+  run(scriptPath('generate_cline_hooks.py'), [CWD]);
   run(scriptPath('generate_roo_rules.py'), [CWD]);
   run(scriptPath('generate_augment_rules.py'), [CWD]);
   run(scriptPath('generate_codex_hooks.py'), [CWD]);
   run(scriptPath('generate_opencode_agents.py'), [CWD]);
   run(scriptPath('generate_opencode_commands.py'), [CWD]);
+  run(scriptPath('generate_opencode_skills.py'), [CWD]);
   run(scriptPath('generate_opencode_plugin.py'), [CWD]);
   run(scriptPath('generate_opencode_json.py'), [CWD]);
   // Single-file generators
@@ -649,12 +671,14 @@ const SPECIAL_HANDLERS = {
   'cursor-mdc':   (_args) => run(scriptPath('generate_cursor_mdc.py'), [CWD]),
   'windsurf-dir-rules': (_args) => run(scriptPath('generate_windsurf_rules.py'), [CWD]),
   'cline-dir-rules': (_args) => run(scriptPath('generate_cline_rules.py'), [CWD]),
+  'cline-hooks': (_args) => run(scriptPath('generate_cline_hooks.py'), [CWD]),
   'roo-dir-rules': (_args) => run(scriptPath('generate_roo_rules.py'), [CWD]),
   'conventions-md': (_args) => { const out = runGenerator('generate_conventions.py'); fs.writeFileSync(path.join(CWD, 'CONVENTIONS.md'), out); console.log('Generated: CONVENTIONS.md'); },
   'augment-dir-rules': (_args) => run(scriptPath('generate_augment_rules.py'), [CWD]),
   'codex-hooks': (_args) => run(scriptPath('generate_codex_hooks.py'), [CWD]),
   'opencode-agents': (_args) => run(scriptPath('generate_opencode_agents.py'), [CWD]),
   'opencode-commands': (_args) => run(scriptPath('generate_opencode_commands.py'), [CWD]),
+  'opencode-skills': (_args) => run(scriptPath('generate_opencode_skills.py'), [CWD]),
   'opencode-plugin': (_args) => run(scriptPath('generate_opencode_plugin.py'), [CWD]),
   'opencode-json': (_args) => run(scriptPath('generate_opencode_json.py'), [CWD]),
   'generate-all': handleGenerateAll,