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.
npx skills add GoldenWing-360/claude-security-skills --skill github-actions-securitygit clone --depth 1 https://github.com/GoldenWing-360/claude-security-skillsWrote 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/goldenwing-360/claude-security-skills/github-actions-security)<a href="https://agentmods.dev/skills/goldenwing-360/claude-security-skills/github-actions-security"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/github-actions-security/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/goldenwing-360/claude-security-skills/github-actions-security"><img src="https://agentmods.dev/badge/skills/goldenwing-360/claude-security-skills/github-actions-security.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 | $0.00080 | $0.02636 |
| Opus 5.5 | $0.00032 | $0.01054 |
| Sonnet 5.5 | $0.00016 | $0.00527 |
| Haiku 4.5 | $0.00008 | $0.00264 |
Grade B, and why
github-actions-security scanned grade B with 1 finding 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 1mo 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
GitHub Action expressions interpolate strings into shell scripts. Untrusted input that contains `; rm -rf /` becomes that, executed. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Actions Security
GitHub Actions runs code with access to your secrets, your code, and increasingly your cloud accounts. Most teams ship workflows with the defaults, which are convenient but expose more than necessary. This skill is the working baseline for production-grade Actions usage.
When to invoke
- Adding a new workflow
- Introducing a third-party action (
uses: someone/some-action@v1) - A workflow leaked a secret (cleanup + prevention)
- Migrating from long-lived cloud credentials to OIDC
- Periodic audit of
.github/workflows/ - Inheriting a repo with unfamiliar workflows
Rule 1 — Pin third-party actions to commit SHA
uses: someone/action@v1 looks safe. It's not. Tags and branches can be moved at any time. If the action's maintainer is compromised, every workflow using @v1 runs the new attacker code on next CI.
Pin to a commit SHA. Comment the version for readability:
# Bad
- uses: actions/checkout@v4
# Good
- uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
For your own org / first-party actions, tag pinning is acceptable because you control the tag. For external actions: SHA pin.
dependabot can update SHA pins automatically — turn it on for .github/workflows/:
# .github/dependabot.yml
version: 2
updates:
- package-ecosystem: github-actions
directory: /
schedule: { interval: weekly }
Rule 2 — Scope GITHUB_TOKEN permissions
GITHUB_TOKEN is created per workflow run. Its default permissions are broad — write to repo contents, issues, PRs, packages. Most workflows need read.
Set the floor at the workflow level, raise per-job only when needed:
name: CI
# Workflow-level default — read-only
permissions:
contents: read
jobs:
test:
runs-on: ubuntu-latest
# inherits read-only
steps:
- uses: actions/checkout@<sha>
- run: npm test
release:
runs-on: ubuntu-latest
needs: test
# Raise only for this job
permissions:
contents: write # for creating tags/releases
packages: write # for publishing
steps:
- uses: actions/checkout@<sha>
- run: npm publish
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.
- 1mo ago First seen · 251 lines · 80 tokens per session scan B 3a76776c3324
github-actions-security is a skill published in the GitHub repository GoldenWing-360/claude-security-skills (20 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 2,636 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
devops-engineer
Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates. Handles deployment automation, GitOps configuration, incident response runbooks, and internal developer platform tooling. Use when setting up CI/CD pipelines, containerizing…
design-loop
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously…
google-apps-script
Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…
cloudflare-api
Hit the Cloudflare REST API directly for operations that wrangler and MCP can't handle well. Bulk DNS, custom hostnames, email routing, cache purge, WAF rules, redirect rules, zone settings, Worker routes, D1 cross-database queries, R2 bulk operations, KV bulk read/write, Vectorize queries, Queues, and fleet-wide…
color-palette
Generate complete, accessible colour palettes from a single brand hex. Produces 11-shade scale (50-950), semantic tokens, dark mode variants, Tailwind v4 CSS output, WCAG contrast checks. Use whenever the user supplies a brand hex and asks for a palette, mentions setting up a design system, wants Tailwind theme…
deep-research
Deep research and discovery before building something new. Explores local projects for reusable code, researches competitors, reads forums and reviews, analyses plugin ecosystems, investigates technical options, and produces a comprehensive research brief. Three depths: focused (30 min), wide (1-2 hours), deep (3-6…