Skip to content
Back to search

coding-agents-skills

MarketplaceWorks with Claude CodeGitHub

Reusable skills for coding agents

Safety scan

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

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/ggarber--coding-agents-skills/badge.svg)](/listings/ggarber--coding-agents-skills)

HTML

<a href="/listings/ggarber--coding-agents-skills"><img src="/api/listings/ggarber--coding-agents-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

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

From GitHub, as a Claude Code plugin (recommended)

The repo is a Claude Code plugin marketplace, so Claude Code can install it straight from GitHub. There's nothing to clone or copy. In a Claude Code session:

/plugin install coding-agents-skills --marketplace ggarber/coding-agents-skills

Or from a shell (pick the scope):

claude plugin marketplace add ggarber/coding-agents-skills
claude plugin install coding-agents-skills@coding-agents-skills --scope user     # the whole computer
claude plugin install coding-agents-skills@coding-agents-skills --scope project  # this project, committed in .claude/settings.json
claude plugin install coding-agents-skills@coding-agents-skills --scope local    # this project, just you

Plugin skills are namespaced: run `/coding-agents-skills:issue-monitor`, or just ask ("monitor the GitHub issues").

- **Updates:** `claude plugin marketplace update coding-agents-skills && claude plugin update coding-agents-skills@coding-agents-skills`, or turn on auto-update for the marketplace in `/plugin` → Marketplaces. The plugin has no pinned `version`, so every new commit is an update. - **Teammates (project scope):** the committed `.claude/settings.json` declares the marketplace and enables the plugin. Each teammate still runs the `claude plugin install ... --scope project` line once per clone. - **Remove:** `claude plugin uninstall coding-agents-skills@coding-agents-skills`.

Without the plugin system

Claude Code also loads skills from plain folders:

| Where | Path | Who gets it | | --- | --- | --- | | The whole computer | `~/.claude/skills/<name>/` | You, in every project | | One project | `<project>/.claude/skills/<name>/` | Everyone who works on that project |

A skill is just its folder (`SKILL.md` plus scripts), so installing means putting that folder, or a link to it, in one of those paths. Start a new Claude Code session afterwards. The skill shows up in `/skills`, and you can call it by name (`/issue-monitor`) or just ask for it.

On the whole computer

Clone once and link the skills, so a `git pull` updates them everywhere:

git clone https://github.com/ggarber/coding-agents-skills.git ~/projects/coding-agents-skills
mkdir -p ~/.claude/skills

# one skill
ln -s ~/projects/coding-agents-skills/skills/issue-monitor ~/.claude/skills/issue-monitor

# or every skill in the repo (re-run after pulling new skills)
for d in ~/projects/coding-agents-skills/skills/*/; do ln -sfn "$d" ~/.claude/skills/"$(basename "$d")"; done

Update: `git -C ~/projects/coding-agents-skills pull`.

In one project, shared through its repo

Add this repo as a git submodule and link the skill into `.claude/skills`. The link and the submodule are committed, so anyone who clones the project gets the skill at the version you pinned:

cd <project>
git submodule add https://github.com/ggarber/coding-agents-skills.git .claude/vendor/coding-agents-skills
mkdir -p .claude/skills
ln -s ../vendor/coding-agents-skills/skills/issue-monitor .claude/skills/issue-monitor
git add .gitmodules .claude && git commit -m "chore: add issue-monitor skill"

- Cloning the project: `git clone --recurse-submodules <url>`, or `git submodule update --init` in an existing clone. Without it the link points at an empty folder and the skill doesn't load. - Updating to the latest skills: `git submodule update --remote .claude/vendor/coding-agents-skills`, then commit the new submodule commit. - Add the project's own rules for the skill in `.claude/<name>.md` (see below).

In one project, as a plain copy

No submodule, no link: copy the folder in and commit it. It won't update by itself; copy it again to update.

mkdir -p <project>/.claude/skills
cp -R ~/projects/coding-agents-skills/skills/issue-monitor <project>/.claude/skills/

Check and remove

ls -l ~/.claude/skills/ <project>/.claude/skills/    # what's installed and where links point

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.

.claude-plugin/marketplace.json · Manifest · 12 lines
  1. {
  2. "name": "coding-agents-skills",
  3. "description": "Reusable skills for coding agents",
  4. "owner": { "name": "Gustavo Garcia" },
  5. "plugins": [
  6. {
  7. "name": "coding-agents-skills",
  8. "source": "./",
  9. "description": "Reusable skills for coding agents: issue-monitor (GitHub issues to merged PRs, with webhook push)"
  10. }
  11. ]
  12. }
README.md · README · 183 lines
  1. # coding-agents-skills
  2. Reusable skills for coding agents (Claude Code and others that read `SKILL.md` skills). Each skill lives in `skills/<name>/` with a `SKILL.md` and any scripts it needs, and stays project-agnostic: project specifics go in the project, not here.
  3. | Skill | What it does |
  4. | --- | --- |
  5. | [`issue-monitor`](skills/issue-monitor/SKILL.md) | Watches a GitHub repo, turns each new issue into a tested, merged PR, and keeps answering comments. Events are pushed to the machine through GitHub webhooks, with cheap polling as a fallback. [`multi.py`](#watching-several-projects-multipy) runs it on several projects at once. |
  6. ## Install
  7. ### From GitHub, as a Claude Code plugin (recommended)
  8. The repo is a Claude Code plugin marketplace, so Claude Code can install it straight from GitHub. There's nothing to clone or copy. In a Claude Code session:
  9. ```
  10. /plugin install coding-agents-skills --marketplace ggarber/coding-agents-skills
  11. ```
  12. Or from a shell (pick the scope):
  13. ```bash
  14. claude plugin marketplace add ggarber/coding-agents-skills
  15. claude plugin install coding-agents-skills@coding-agents-skills --scope user # the whole computer
  16. claude plugin install coding-agents-skills@coding-agents-skills --scope project # this project, committed in .claude/settings.json
  17. claude plugin install coding-agents-skills@coding-agents-skills --scope local # this project, just you
  18. ```
  19. Plugin skills are namespaced: run `/coding-agents-skills:issue-monitor`, or just ask ("monitor the GitHub issues").
  20. - **Updates:** `claude plugin marketplace update coding-agents-skills && claude plugin update coding-agents-skills@coding-agents-skills`, or turn on auto-update for the marketplace in `/plugin` → Marketplaces. The plugin has no pinned `version`, so every new commit is an update.
  21. - **Teammates (project scope):** the committed `.claude/settings.json` declares the marketplace and enables the plugin. Each teammate still runs the `claude plugin install ... --scope project` line once per clone.
  22. - **Remove:** `claude plugin uninstall coding-agents-skills@coding-agents-skills`.
  23. ### Without the plugin system
  24. Claude Code also loads skills from plain folders:
  25. | Where | Path | Who gets it |
  26. | --- | --- | --- |
  27. | The whole computer | `~/.claude/skills/<name>/` | You, in every project |
  28. | One project | `<project>/.claude/skills/<name>/` | Everyone who works on that project |
  29. A skill is just its folder (`SKILL.md` plus scripts), so installing means putting that folder, or a link to it, in one of those paths. Start a new Claude Code session afterwards. The skill shows up in `/skills`, and you can call it by name (`/issue-monitor`) or just ask for it.
  30. #### On the whole computer
  31. Clone once and link the skills, so a `git pull` updates them everywhere:
  32. ```bash
  33. git clone https://github.com/ggarber/coding-agents-skills.git ~/projects/coding-agents-skills
  34. mkdir -p ~/.claude/skills
  35. # one skill
  36. ln -s ~/projects/coding-agents-skills/skills/issue-monitor ~/.claude/skills/issue-monitor
  37. # or every skill in the repo (re-run after pulling new skills)
  38. for d in ~/projects/coding-agents-skills/skills/*/; do ln -sfn "$d" ~/.claude/skills/"$(basename "$d")"; done
  39. ```
  40. Update: `git -C ~/projects/coding-agents-skills pull`.
  41. #### In one project, shared through its repo
  42. Add this repo as a git submodule and link the skill into `.claude/skills`. The link and the submodule are committed, so anyone who clones the project gets the skill at the version you pinned:
  43. ```bash
  44. cd <project>
  45. git submodule add https://github.com/ggarber/coding-agents-skills.git .claude/vendor/coding-agents-skills
  46. mkdir -p .claude/skills
  47. ln -s ../vendor/coding-agents-skills/skills/issue-monitor .claude/skills/issue-monitor
  48. git add .gitmodules .claude && git commit -m "chore: add issue-monitor skill"
  49. ```
  50. - Cloning the project: `git clone --recurse-submodules <url>`, or `git submodule update --init` in an existing clone. Without it the link points at an empty folder and the skill doesn't load.
  51. - Updating to the latest skills: `git submodule update --remote .claude/vendor/coding-agents-skills`, then commit the new submodule commit.
  52. - Add the project's own rules for the skill in `.claude/<name>.md` (see below).
  53. #### In one project, as a plain copy
  54. No submodule, no link: copy the folder in and commit it. It won't update by itself; copy it again to update.
  55. ```bash
  56. mkdir -p <project>/.claude/skills
  57. cp -R ~/projects/coding-agents-skills/skills/issue-monitor <project>/.claude/skills/
  58. ```
  59. #### Check and remove
  60. ```bash
  61. ls -l ~/.claude/skills/ <project>/.claude/skills/ # what's installed and where links point
  62. python3 ~/.claude/skills/issue-monitor/watch.py --help # the skill's scripts run from there
  63. rm ~/.claude/skills/issue-monitor # remove a linked skill (the clone stays)
  64. ```
  65. Install a skill in one place only. With the same skill both on the computer and in a project, or both as a plugin and as a folder, it's unclear which copy the agent uses.
  66. ### Other agents
  67. Agents that don't load `SKILL.md` skills can still follow them: point them at `skills/<name>/SKILL.md` from the project's `AGENTS.md` (or equivalent), for example "To work GitHub issues, follow `.claude/vendor/coding-agents-skills/skills/issue-monitor/SKILL.md`."
  68. ## Project-specific rules
  69. Skills read the project's `CLAUDE.md` / `AGENTS.md`. A skill can also read its own project file: `issue-monitor` reads `.claude/issue-monitor.md` if it exists. Put things there like which app vague issues usually mean, the checks to run, end-to-end recipes, and what must never be deployed without an explicit ask.
  70. ## issue-monitor
  71. ### Requirements
  72. - [`gh`](https://cli.github.com/) logged in (`gh auth status`) with write access to the repo.
  73. - Python 3.8+ (only the standard library).
  74. ### Push notifications instead of polling
  75. GitHub can't reach a laptop directly, but the official [`gh webhook`](https://docs.github.com/en/webhooks/testing-and-troubleshooting-webhooks/using-the-github-cli-to-forward-webhooks-for-testing) extension relays a repo's webhooks over an outbound connection. No public URL, tunnel or server is needed. When it's installed, the watcher uses it and reacts to new issues, comments, review comments and pushes within a second or two:
  76. ```bash
  77. gh extension install cli/gh-webhook
  78. ```
  79. The skill installs it itself when the agent is allowed to.
  80. Notes:
  81. - The forwarder creates a temporary webhook on the repo, so you need admin rights on it. The default `gh auth login` token is enough for your own repos; if creating the hook fails with 403/404, run `gh auth refresh -s admin:repo_hook`.
  82. - GitHub allows one active forwarder per repo, so run one watcher per repo at a time.
  83. - Stop the watcher with Ctrl-C / SIGTERM so it removes the hook. After a hard kill, the next start logs `Hook already exists` and retries until GitHub drops the old one.
  84. - The forwarder is meant for development. If it drops, the watcher keeps polling and retries the forward.
  85. - Measured: a new issue or comment reaches the watcher in about 2 s, with the poll interval set to 5 minutes.
  86. Without the extension, the watcher polls every 15 s with conditional requests (`If-None-Match` + ETag). An unchanged answer is a `304 Not Modified`, which [doesn't count against the rate limit](https://docs.github.com/en/rest/using-the-rest-api/best-practices-for-using-the-rest-api#use-conditional-requests-if-appropriate), so even fast polling costs almost nothing. Webhook deliveries are reported straight from their payload, and the poll catches anything they missed. Both paths share one record of what was reported, so each event is printed once.
  87. ### Running the watcher by hand
  88. ```bash
  89. python3 skills/issue-monitor/watch.py # repo of the current directory
  90. python3 skills/issue-monitor/watch.py owner/repo --branches main,dev --interval 10
  91. python3 skills/issue-monitor/watch.py --once --no-react # one check, no 👀 reactions
  92. python3 skills/issue-monitor/watch.py --help
  93. ```
  94. It prints one line per event on stdout (`NEW_ISSUE`, `NEW_COMMENT`, `NEW_REVIEW_COMMENT`, `NEW_COMMIT`) and status on stderr. In Claude Code, the skill runs it under the Monitor tool, so each line reaches the agent as soon as it's printed. State is in `~/.cache/coding-agents-skills/watch/<owner>_<repo>.json`. Delete it to replay the last day (commits seen on the first run are recorded, not reported).
  95. Comments containing `<!-- claude-issue-monitor -->` are skipped. The agent ends all of its comments with that marker, so it never answers itself when it posts from the owner's account. Change it with `--marker`.
  96. ## Watching several projects: multi.py
  97. `multi.py` starts one Claude Code session per project folder, each running `issue-monitor`. For each folder it first copies the skill into `<folder>/.claude/skills/issue-monitor`, then starts the session with `/issue-monitor`. Python 3.8+, standard library only (PyYAML is used if present).
  98. ```bash
  99. cp config.example.yaml config.yaml # then list your folders in it
  100. ./multi.py # folders from config.yaml
  101. ./multi.py ~/projects/app-one ~/projects/app-two # or pass them directly
  102. ./multi.py --dry-run # print what would happen, change nothing
  103. ./multi.py --copy-only # copy the skill into the folders, don't launch
  104. ./multi.py --stop # stop the tmux sessions
  105. ```
  106. `config.yaml` (ignored by git):
  107. ```yaml
  108. folders:
  109. - ~/projects/app-one
  110. - ~/projects/app-two
  111. permission_mode: auto # unattended sessions need a mode that doesn't stop at prompts
  112. # claude_args: [--model, opus] # extra arguments for every session
  113. # prompt: /issue-monitor # first message (the default)
  114. ```
  115. - **The copy:** every run refreshes it from this clone, so `git pull` here and re-run to update the projects. The copy is listed in the project's `.git/info/exclude`, so it never shows up in `git status` or gets committed. A project that already has the skill as a symlink or a committed folder keeps its own (it's skipped).
  116. - Each session runs in its own tmux session (`tmux attach -t issues-<folder>`) when tmux is installed, otherwise in a new Terminal window (macOS).
  117. - Folders that aren't the root of a git repository are skipped. Run one session per GitHub repo: GitHub allows one webhook forwarder per repo.
  118. - Without `permission_mode`, each session waits for you to approve its commands. Pick the mode you're comfortable leaving unattended. The skill still never deploys or merges red, but the agent pushes branches and merges PRs on its own.
  119. - Closing a window or `--stop` ends the session, and the watcher removes its temporary webhook on the way out.
  120. ## Adding a skill
  121. 1. `skills/<name>/SKILL.md` with `name` and `description` front matter. The description says when to use the skill. Refer to bundled scripts as `${CLAUDE_SKILL_DIR}/<script>`, which works for plugin and folder installs alike.
  122. 2. Keep it generic: read project rules from the project (`CLAUDE.md`, `AGENTS.md`, `.claude/<name>.md`) instead of hard-coding them.
  123. 3. Scripts next to `SKILL.md`, standard library only where possible, with `--help`.
  124. 4. Add a row to the table above, and check the plugin with `claude plugin validate .`.
  125. ## License
  126. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

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