github-actions

github-actions is a skill for Claude Code, Codex from tartinerlabs/skills. It costs 34 tokens per session (1,135 once invoked), scanned A, original, MIT.

A guide to GitHub Actions, GitHub's system for automatically running tasks such as tests and deployments. It creates or reviews CI/CD workflows, which automate checks and delivery when code changes.

In plain words
What is it for?
Use it to create or audit CI/CD workflows, add project checks, fix action pinning, and review existing GitHub Actions configuration.
Why use it?
It helps ensure workflows use appropriate permissions and pin third-party actions to specific versions identified by commit hashes.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/tartinerlabs/skills/github-actions
Any agent
npx skills add tartinerlabs/skills --skill github-actions
Clone the repo
git clone --depth 1 https://github.com/tartinerlabs/skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for github-actions

README.md
[![agentmods](https://agentmods.dev/badge/skills/tartinerlabs/skills/github-actions.svg)](https://agentmods.dev/skills/tartinerlabs/skills/github-actions)
Your own site
<a href="https://agentmods.dev/skills/tartinerlabs/skills/github-actions"><img src="https://agentmods.dev/badge/skills/tartinerlabs/skills/github-actions.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,135 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.01135
Opus 5 $0.00017 $0.00567
Sonnet 5 $0.00007 $0.00227
Haiku 4.5 $0.00003 $0.00113

Measured 4d ago against content hash 058a890a2095, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-actions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/github-actions/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mode Detection

Audit and report by default. Generate workflows only when asked to create, add, or set up CI — and never merely because .github/workflows/ is absent; report that none were found instead. Apply fixes only when asked to fix or pin. When the ask is unclear, report and offer to apply the fixes.

Create Mode

1. Detect Project Type

Scan for project indicators:

  • package.json → Node.js/JS/TS
  • go.mod → Go
  • requirements.txt / pyproject.toml / setup.py → Python
  • Cargo.toml → Rust
  • Gemfile → Ruby

2. Detect Package Manager (JS/TS projects)

Detect the package manager from the lockfile, in this order: nub.lock, pnpm-lock.yaml, bun.lock/bun.lockb, yarn.lock, package-lock.json. With no lockfile, ask.

A packageManager or devEngines.packageManager field in package.json outranks any lockfile. Nub runs in compat-mode over another manager's lockfile, so nub.lock alongside pnpm-lock.yaml means nub — check the field before concluding from lockfiles alone.

3. Generate Workflow

Read each rule file in rules/ and apply all of them when generating workflows.

Pin every action per rules/action-pinning.md before writing the workflow, including GitHub-owned actions/*. Resolve the intended release or source ref to a full commit SHA with gh api repos/{owner}/{repo}/commits/{ref} --jq '.sha', then retain the release or source ref in a comment.

4. Workflow Template

Route by the language detected in Step 1. The template below is the JS/TS default; for any other detected language, load references/<lang>.md and use its template instead:

Language Template
JS/TS (Node) the template below
Go references/go.md
Python references/python.md
Rust references/rust.md
Ruby references/ruby.md

Every template applies the same rules/ (action pinning, permissions, concurrency). Adapt the JS/TS template to the detected package manager (replace <pm> with the detected package manager):

Read the full file on GitHub · 115 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 115 lines · 34 tokens per session scan A 058a890a2095

Subscribe to this mod's changes

github-actions is a skill published in the GitHub repository tartinerlabs/skills (7 stars, last pushed 11d ago), licensed MIT. It adds 34 tokens to every session and 1,135 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.