Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/alivirgo/Major-AI-Skillsnpx agentmods add skills/alivirgo/major-ai-skills/github-actionsWrote 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.
[](https://agentmods.dev/skills/alivirgo/major-ai-skills/github-actions)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/github-actions"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/github-actions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/github-actions"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/github-actions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.01753 |
| Opus 5.5 | $0.00016 | $0.00701 |
| Sonnet 5.5 | $0.00008 | $0.00351 |
| Haiku 4.5 | $0.00004 | $0.00175 |
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 18d 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Actions CI/CD AI Skill Guide (Claude)
Overview & Engine Architecture
GitHub Actions runs workflows (YAML under .github/workflows/) on events (push, pull_request, workflow_dispatch, …). Jobs execute on runners; steps use run: or actions from the marketplace. Security is the product: explicit permissions, OIDC federation instead of long-lived cloud keys, pinned action SHAs for high assurance, and fork PR rules that block secrets and OIDC by design.
┌─────────────────────────────────────────────────────────────┐
│ GitHub Actions trust model │
│ │
│ Event → workflow → job(s) → steps │
│ ├── GITHUB_TOKEN (scoped by permissions: block) │
│ ├── Repository / environment secrets │
│ └── OIDC JWT (id-token: write) → cloud IAM role │
│ │
│ Reusable workflow: caller permissions CAP callee │
│ Fork pull_request: read-only token; NO OIDC injection │
└─────────────────────────────────────────────────────────────┘
When to use / when not to
Use when
- Adding CI (lint/test/build) on PRs and release/deploy on protected branches.
- Wiring AWS/GCP/Azure login via OIDC; caching dependencies; matrix builds.
- Debugging failed checks, cache misses, permission errors, or reusable workflow auth.
Do not use when
pull_request_targetis suggested to “fix” fork OIDC while checking out untrusted PR code—refuse; use maintainer-triggered workflows or skip cloud steps on forks.- Long-lived cloud access keys in repo secrets when OIDC is available.
- Running unreviewed third-party actions with write permissions.
Operational Capabilities & Agent Directives
- Set
permissions:explicitly at workflow or job level; listing scopes replaces repo defaults—include everything needed (contents: read,pull-requests: write, etc.). - OIDC jobs require
id-token: writeon the caller when using reusable workflows; callee cannot exceed caller caps. - Fork PRs: assume no secrets, no OIDC; gate cloud deploy steps with
if: github.event.pull_request.head.repo.full_name == github.repositoryor manualworkflow_dispatch. - Pin actions to full commit SHA for deploy workflows; at minimum pin major tags you trust for inner loops.
- Never echo secrets; use
maskpatterns; rotate if leaked in logs. - Cache keys must hash lockfiles (
package-lock.json,poetry.lock,go.sum). - Separate PR CI from production deploy workflows; use environments with required reviewers for prod.
- Supply chain: audit what marketplace actions execute; prefer composite actions you own.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 18d ago Changed · +70 lines · +12 tokens per session d8f02c909a2b
- 1mo ago Changed · -2 tokens per session 6d4309158a2b
- 1mo ago First seen · 117 lines · 31 tokens per session scan A abcedde0032c
github-actions is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,753 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
GitHub Actions Workflow Security Review
Reviews GitHub Actions workflow diffs for script injection of untrusted input, pullrequesttarget with untrusted checkout, over-broad GITHUBTOKEN permissions, and unpinned third-party actions.
devops-cicd
CI/CD pipelines, infrastructure as code, and deployment strategies.
securing-github-actions-workflows
This skill covers hardening GitHub Actions workflows against supply chain attacks, credential theft, and privilege escalation. It addresses pinning actions to SHA digests, minimizing GITHUBTOKEN permissions, protecting secrets from exfiltration, preventing script injection in workflow expressions, and implementing…
github-actions
Use when authoring or fixing GitHub Actions CI/CD — workflows under .github/workflows, triggers, job matrix, caching, token permissions, OIDC cloud deploys, environment gates, reusable workflows. NOT the Dockerfile or image build strategy (that is docker), NOT the branching model (that is git-workflow), NOT release…
GitHub CI Fix Debugging
Debug and fix failing GitHub PR checks by inspecting GitHub Actions logs, summarizing failure context, drafting fix plans, and implementing fixes after approval.
deployment
Use when taking an app from source to live: choosing the deploy target from requirements (Hetzner+Coolify vs Vercel vs a third), then wiring container → CI → registry → host with build secrets, healthchecks and rollback. NOT one platform's mechanics (that is coolify, vercel, railway, render), NOT the Dockerfile alone…