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/mthines/agent-skillsnpx agentmods add skills/mthines/agent-skills/github-actions-authorWrote 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/mthines/agent-skills/github-actions-author)<a href="https://agentmods.dev/skills/mthines/agent-skills/github-actions-author"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/github-actions-author/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/mthines/agent-skills/github-actions-author"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/github-actions-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 218 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00220 | $0.04478 |
| Opus 5.5 | $0.00088 | $0.01791 |
| Sonnet 5.5 | $0.00044 | $0.00896 |
| Haiku 4.5 | $0.00022 | $0.00448 |
Grade A, and why
github-actions-author 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 19d 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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Actions Author
Generate or audit GitHub Actions workflow YAML against 2026 best practices for speed, cost, reusability, and security.
This
SKILL.mdis a thin index. Detailed rules live inrules/*.mdand load on demand. Drop-in starters live intemplates/*.md. The decision tree for picking a shape lives inreferences/decision-tree.md.
Non-negotiable — every step's output reaches the run log
This applies to both modes and outranks every other preference in this skill.
Every command in every scaffolded or reviewed workflow must write its stdout and stderr to the job log.
Output that lands only in a file, only in an artifact, only in $GITHUB_STEP_SUMMARY, or in /dev/null is invisible to gh run view <run-id> --log-failed — the only surface /ci-auto-fix, /implement-suggestion, and an on-call human read a failure from.
A failing step that printed nothing cannot be diagnosed or fixed by an agent; it can only be escalated.
Minimum bar for every run: block:
- name: Run unit tests
shell: bash
run: |
set -euo pipefail
npm test 2>&1 | tee test-output.log # tee, never `> file`
Forbidden outright: > /dev/null, 2>/dev/null, cmd > out.txt 2>&1, --silent, --quiet, -q, a machine-only reporter with no human output, and || true without echoing the captured output and exit code.
tee requires set -o pipefail, otherwise the step goes green on a failed command.
Full rule, decision table, examples, and the review-mode grep:
rules/log-output-visibility.md — read it in Phase 4 of scaffold and in every review.
Mode Detection
Parse $ARGUMENTS (first token):
| Mode | Default | Trigger |
|---|---|---|
scaffold |
yes | Default. "create", "scaffold", "new workflow", or no token. |
review |
"review", "audit", path to an existing .github/workflows/*. |
What ships with it
15 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.
- references/decision-tree.md 7.8 KB
- rules/caching.md 7.6 KB
- rules/feedback.md 12 KB
- rules/log-output-visibility.md 7.3 KB
- rules/observability.md 8.4 KB
- rules/parallelization.md 7.6 KB
- rules/reusability.md 7.9 KB
- rules/security.md 9.8 KB
- rules/triggers-and-concurrency.md 7.6 KB
- rules/workflow-anatomy.md 6.7 KB
- templates/composite-action.yml.md 1.9 KB
- templates/deploy-oidc.yml.md 2.9 KB
- templates/node-ci.yml.md 3.6 KB
- templates/python-ci.yml.md 3.4 KB
- templates/reusable-workflow.yml.md 2.9 KB
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.
- 19d ago Changed a4de628712e2
- 1mo ago First seen · 354 lines · 220 tokens per session scan A f34aab8cb36b
github-actions-author is a skill published in the GitHub repository mthines/agent-skills (19 stars, last pushed today), licensed MIT. It adds 220 tokens to every session and 4,478 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
ci-cd-and-automation
Guides CI/CD pipeline design — quality gates, GitHub Actions for Go/TypeScript/PHP, feature-flag-decoupled deploys, secrets scoping, and pipeline optimization. Use when setting up or modifying a build/test/deploy pipeline, adding an automated quality gate, configuring CI secrets, or diagnosing a slow or flaky…
laravel-verification
Use when asked to verify a Laravel project before a PR, after a major refactor or dependency upgrade, or before deploying to staging/production. Runs a phased env-check -> lint -> test -> security -> migration -> deploy-readiness -> queue pipeline, stopping at the first failing gate rather than reporting every phase's…
ci-cd-and-automation
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
google-cloud-slo-alert-configuration
Configures Cloud Monitoring PromQL-based Service Level Objective (SLO) alerting policies on Google Cloud for resources registered in App Hub or individually specified. Generates Terraform output. Use when the user asks to configure an SLO or Service Level Objective. Don't use for standard alerting policies.
skill-body
Call help() or help("page.click") to print signatures and uncommon options of APIs named below; it prints by itself, so do not wrap it in console.log. For installation or connection problems, read references/install.md in the ego-browser Skill directory.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.