Skip to content
Back to search

codex-skills

SkillWorks with CodexGitHub

A collection of Codex/agent skills for planning, documentation access, frontend development, and browser automation.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/am-will-codex-skills/badge.svg)](/listings/am-will-codex-skills)

HTML

<a href="/listings/am-will-codex-skills"><img src="/api/listings/am-will-codex-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Install skills using the [skills.sh](https://skills.sh) CLI:

# List available skills before installing
npx skills add am-will/codex-skills --list

# Install specific skills to user scope (global)
npx skills add am-will/codex-skills --skill planner --skill context7 -g

# Install all skills interactively (prompts for selection)
npx skills add am-will/codex-skills -g

# Install to specific agents
npx skills add am-will/codex-skills --skill planner -a claude-code -a codex -g

# Install to current project (instead of global)
npx skills add am-will/codex-skills --skill planner

# Non-interactive install (skip prompts)
npx skills add am-will/codex-skills --skill planner -g -y

**CLI Options:** | Flag | Purpose | |------|---------| | `-g, --global` | Install to user directory (global for all projects) | | `-a, --agent <agents...>` | Target specific agents (`claude-code`, `codex`, etc.) | | `-s, --skill <skills...>` | Install specific skills by name | | `-l, --list` | List available skills without installing | | `-y, --yes` | Skip confirmation prompts |

**Other commands:**

npx skills list          # Show installed skills
npx skills remove <name> # Uninstall a skill
npx skills update        # Update all installed skills

**Note on Browser Tools**: The repo includes two browser automation tools (`gemini-computer-use` and `agent-browser`). You don't need to install both - choose the one that best fits your workflow. I recommend agent-browser for speed and simplicity.

**Note on Context7**: The `ctx7old` skill requires a Context7 API key in `CONTEXT7_API_KEY`. See `skills/ctx7old/.env.example` for setup.

**Note on Gemini Computer Use Skill**: This skill requires a GEMINI_API_KEY. Ask Codex to help you set it up.

**Note on llm-council**: This skill requires API keys or Active Subscriptions for multiple providers (Claude/Anthropic, OpenAI for Codex, Google for Gemini). Run `./setup.sh` in the skill directory to configure. Includes a real-time web UI that auto-launches during planning sessions.

---

Codex Hook Catalog

The `hooks/` directory contains a catalog of **51 ready-to-install Codex hook bundles**, generated from an upstream hook template set and adapted for the current Codex event model. The active catalog now includes the former file-edit bundles that became viable once Codex started emitting `apply_patch` hook events with `Edit` and `Write` matcher compatibility.

**Categories:**

| Category | Bundles | Examples | |---|---|---| | `automation` | 18 | Slack/Discord/Telegram notifications, deployment health monitor, AGENTS loader, build/dependency automation | | `development-tools` | 8 | Command logger, debug window, worktree ghostty, file backup, lint/format helpers | | `git` | 3 | Conventional commits, prevent direct push, validate branch name | | `git-workflow` | 2 | Auto git add, smart commit | | `monitoring` | 2 | Desktop notification on stop, LangSmith tracing | | `performance` | 2 | Performance monitor, performance budget guard | | `post-tool` | 4 | Format JS/Python, git add changes, run tests after changes | | `pre-tool` | 4 | Notify before bash, update search year, backup before edit, console log cleaner | | `quality-gates` | 3 | Scope guard, plan gate, TDD gate | | `security` | 4 | Dangerous command blocker, secret scanner, file protection, security scanner | | `testing` | 1 | Test runner |

**Install a bundle:**

python3 hooks/aitmpl-codex/install-bundle.py hooks/aitmpl-codex/<category>/<bundle> <target-repo>

**Manual install:** Copy the bundle's `hooks.json` into `<repo>/.codex/hooks.json` and its `.codex/hooks/` scripts into `<repo>/.codex/hooks/`, then restart Codex.

See [`hooks/README.md`](hooks/README.md) for full details on compatibility, testing harness, and bundle structure.

---

Custom Multi-Agents for Codex

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 145 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <img width="750" height="491" alt="image" src="https://github.com/user-attachments/assets/c244cbdd-6f98-40b5-81f0-754aad546be4" />
  2. # CodexSkills
  3. A collection of Codex/agent skills for planning, documentation access, frontend development, and browser automation.
  4. ## Available skills
  5. ### Agent Orchestration
  6. - `planner`:
  7. Create comprehensive, phased implementation plans with sprints and atomic tasks. Use for planning implementations, breaking down features, or creating structured roadmaps.
  8. - `plan-harder`:
  9. Enhanced planning variant for more detailed analysis and task breakdown.
  10. - `parallel-task`:
  11. Execute plan files by launching multiple parallel subagents to complete tasks simultaneously. Requires an existing plan file from `planner`.
  12. - `llm-council`:
  13. Multi-agent orchestration system for planning complex tasks. Spawns multiple AI planners (Claude, Codex, Gemini) to generate independent plans, then uses a judge agent to synthesize the best approach. Includes a real-time web UI for monitoring progress and refining plans interactively.
  14. ### Documentation Access
  15. - `ctx7old`:
  16. Fetch up-to-date library documentation via Context7 CLI.
  17. - `openai-docs-skill`:
  18. Query OpenAI developer docs via the OpenAI Docs MCP server using CLI.
  19. - `markdown-url`:
  20. Prefix any website you need to visit with `https://markdown.new/` for a clean, Markdown-friendly view.
  21. - `read-github`:
  22. Read and search GitHub repository documentation via gitmcp.io MCP service. Converts `github.com/owner/repo` URLs to `gitmcp.io/owner/repo` for LLM-friendly access to repos.
  23. ### Prompting
  24. - `gpt-5-6-prompt-builder`:
  25. Build, transform, audit, and migrate prompts for GPT-5.6 Sol. It gathers missing behavior-critical requirements with `request_user_input` when available, then produces an outcome-first prompt with explicit success criteria, guardrails, tools, approvals, validation, and stop rules.
  26. ### Frontend & Design
  27. - `frontend-design`:
  28. Distinctive frontend design system guidance (imported from Anthropic).
  29. - `frontend-responsive-ui`:
  30. Responsive UI standards (imported from Anthropic).
  31. - `vercel-react-best-practices`:
  32. React/Next.js performance guidance (imported from Vercel).
  33. ### Codex Tooling
  34. - `create-hook`:
  35. Create or update Codex hooks for global or project scope. Guides users through scope, hook type, and behavior, then writes hook config and scripts.
  36. - `pluginstaller`:
  37. Install a Codex plugin from a GitHub repo into a repo or personal marketplace. Handles plugin discovery, validation, and marketplace registration.
  38. - `role-creator`:
  39. Create and update custom Codex agents as standalone TOML files. Collects required inputs and writes agent definitions to global or project scope.
  40. ### Browser Automation
  41. - `gemini-computer-use`:
  42. Gemini 2.5 Computer Use browser-control agent skill (Playwright + safety confirmation loop).
  43. - `agent-browser`:
  44. Fast Rust-based headless browser automation CLI from Vercel Labs with snapshot/act pattern for AI agents.
  45. ## Installation
  46. Install skills using the [skills.sh](https://skills.sh) CLI:
  47. ```bash
  48. # List available skills before installing
  49. npx skills add am-will/codex-skills --list
  50. # Install specific skills to user scope (global)
  51. npx skills add am-will/codex-skills --skill planner --skill context7 -g
  52. # Install all skills interactively (prompts for selection)
  53. npx skills add am-will/codex-skills -g
  54. # Install to specific agents
  55. npx skills add am-will/codex-skills --skill planner -a claude-code -a codex -g
  56. # Install to current project (instead of global)
  57. npx skills add am-will/codex-skills --skill planner
  58. # Non-interactive install (skip prompts)
  59. npx skills add am-will/codex-skills --skill planner -g -y
  60. ```
  61. **CLI Options:**
  62. | Flag | Purpose |
  63. |------|---------|
  64. | `-g, --global` | Install to user directory (global for all projects) |
  65. | `-a, --agent <agents...>` | Target specific agents (`claude-code`, `codex`, etc.) |
  66. | `-s, --skill <skills...>` | Install specific skills by name |
  67. | `-l, --list` | List available skills without installing |
  68. | `-y, --yes` | Skip confirmation prompts |
  69. **Other commands:**
  70. ```bash
  71. npx skills list # Show installed skills
  72. npx skills remove <name> # Uninstall a skill
  73. npx skills update # Update all installed skills
  74. ```
  75. **Note on Browser Tools**: The repo includes two browser automation tools (`gemini-computer-use` and `agent-browser`). You don't need to install both - choose the one that best fits your workflow. I recommend agent-browser for speed and simplicity.
  76. **Note on Context7**: The `ctx7old` skill requires a Context7 API key in `CONTEXT7_API_KEY`. See `skills/ctx7old/.env.example` for setup.
  77. **Note on Gemini Computer Use Skill**: This skill requires a GEMINI_API_KEY. Ask Codex to help you set it up.
  78. **Note on llm-council**: This skill requires API keys or Active Subscriptions for multiple providers (Claude/Anthropic, OpenAI for Codex, Google for Gemini). Run `./setup.sh` in the skill directory to configure. Includes a real-time web UI that auto-launches during planning sessions.
  79. ---
  80. ### Codex Hook Catalog
  81. The `hooks/` directory contains a catalog of **51 ready-to-install Codex hook bundles**, generated from an upstream hook template set and adapted for the current Codex event model. The active catalog now includes the former file-edit bundles that became viable once Codex started emitting `apply_patch` hook events with `Edit` and `Write` matcher compatibility.
  82. **Categories:**
  83. | Category | Bundles | Examples |
  84. |---|---|---|
  85. | `automation` | 18 | Slack/Discord/Telegram notifications, deployment health monitor, AGENTS loader, build/dependency automation |
  86. | `development-tools` | 8 | Command logger, debug window, worktree ghostty, file backup, lint/format helpers |
  87. | `git` | 3 | Conventional commits, prevent direct push, validate branch name |
  88. | `git-workflow` | 2 | Auto git add, smart commit |
  89. | `monitoring` | 2 | Desktop notification on stop, LangSmith tracing |
  90. | `performance` | 2 | Performance monitor, performance budget guard |
  91. | `post-tool` | 4 | Format JS/Python, git add changes, run tests after changes |
  92. | `pre-tool` | 4 | Notify before bash, update search year, backup before edit, console log cleaner |
  93. | `quality-gates` | 3 | Scope guard, plan gate, TDD gate |
  94. | `security` | 4 | Dangerous command blocker, secret scanner, file protection, security scanner |
  95. | `testing` | 1 | Test runner |
  96. **Install a bundle:**
  97. ```bash
  98. python3 hooks/aitmpl-codex/install-bundle.py hooks/aitmpl-codex/<category>/<bundle> <target-repo>
  99. ```
  100. **Manual install:** Copy the bundle's `hooks.json` into `<repo>/.codex/hooks.json` and its `.codex/hooks/` scripts into `<repo>/.codex/hooks/`, then restart Codex.
  101. See [`hooks/README.md`](hooks/README.md) for full details on compatibility, testing harness, and bundle structure.
  102. ---
  103. ### Custom Multi-Agents for Codex
  104. The `agents/` directory contains custom multi-agent configurations for Codex. These TOML-based agent definitions provide specialized roles (architect, frontend, backend, security, etc.) and worker tiers for parallel task execution. Use them with Codex to spin up purpose-built agents tailored to your workflow.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.