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 agentmods add skills/akin-ozer/cc-devops-skills/github-actions-generatornpx skills add akin-ozer/cc-devops-skills --skill github-actions-generatorgit clone --depth 1 https://github.com/akin-ozer/cc-devops-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/akin-ozer/cc-devops-skills/github-actions-generator)<a href="https://agentmods.dev/skills/akin-ozer/cc-devops-skills/github-actions-generator"><img src="https://agentmods.dev/badge/skills/akin-ozer/cc-devops-skills/github-actions-generator.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.02841 |
| Opus 5 | $0.00014 | $0.01421 |
| Sonnet 5 | $0.00005 | $0.00568 |
| Haiku 4.5 | $0.00003 | $0.00284 |
Grade A, and why
github-actions-generator 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 3d 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Actions Generator
Generate production-ready GitHub Actions workflows and custom actions following current best practices, security standards, and naming conventions. All generated resources are automatically validated using the devops-skills:github-actions-validator skill.
Quick Reference
| Capability | When to Use | Reference |
|---|---|---|
| Workflows | CI/CD, automation, testing | references/best-practices.md |
| Composite Actions | Reusable step combinations | references/custom-actions.md |
| Docker Actions | Custom environments/tools | references/custom-actions.md |
| JavaScript Actions | API interactions, complex logic | references/custom-actions.md |
| Reusable Workflows | Shared patterns across repos | references/advanced-triggers.md |
| Security Scanning | Dependency review, SBOM | references/best-practices.md |
| Modern Features | Summaries, environments | references/modern-features.md |
Trigger Decision Tree
Route every request through this decision tree before reading references or generating files:
- If the user asks for
.github/workflows/*.ymlCI/CD automation, choose Workflow Generation. - If the user asks for
action.ymlor a reusable step package, choose Custom Action Generation. - If the user asks for
workflow_callor shared pipelines across repositories, choose Reusable Workflow Generation. - If the request includes security-only scanning (dependency review, SBOM, CodeQL), stay on Workflow Generation with the security pattern.
- If intent is ambiguous, ask one disambiguation question: "Do you want a workflow, a custom action, or a reusable workflow?"
Progressive Disclosure Route
Load only what is needed for the selected route, in this order:
| Route | Load First (required) | Load Next (only if needed) | Primary Template |
|---|---|---|---|
| Workflow Generation | references/best-practices.md |
references/common-actions.md, references/expressions-and-contexts.md, references/modern-features.md |
assets/templates/workflow/basic_workflow.yml |
| Custom Action Generation | references/custom-actions.md |
references/best-practices.md |
assets/templates/action/composite/action.yml, assets/templates/action/docker/, assets/templates/action/javascript/ |
| Reusable Workflow Generation | references/advanced-triggers.md |
references/best-practices.md, references/common-actions.md |
assets/templates/workflow/reusable_workflow.yml |
What ships with it
31 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.
- assets/templates/action/composite/action.yml 2.1 KB
- assets/templates/action/docker/action.yml 1.0 KB
- assets/templates/action/docker/Dockerfile 608 B
- assets/templates/action/docker/entrypoint.sh 479 B runs code
- assets/templates/action/javascript/action.yml 824 B
- assets/templates/action/javascript/index.js 1.3 KB runs code
- assets/templates/action/javascript/package.json 585 B
- assets/templates/workflow/basic_workflow.yml 5.7 KB
- assets/templates/workflow/reusable_workflow.yml 2.7 KB
- examples/actions/setup-node-cached/action.yml 2.8 KB
- examples/caching/docker-buildkit.yml 9.4 KB
- examples/README.md 4.2 KB
- examples/security/dependency-review.yml 1.7 KB
- examples/security/sbom-attestation.yml 4.4 KB
- examples/triggers/chatops-commands.yml 16 KB
- examples/triggers/repository-dispatch.yml 13 KB
- examples/triggers/workflow-orchestration.yml 12 KB
- examples/workflows/docker-build-push.yml 2.1 KB
- examples/workflows/go-ci.yml 4.3 KB
- examples/workflows/monorepo-ci.yml 11 KB
- examples/workflows/multi-environment-deploy.yml 13 KB
- examples/workflows/nodejs-ci.yml 3.0 KB
- examples/workflows/python-ci.yml 4.1 KB
- examples/workflows/scheduled-tasks.yml 14 KB
- references/advanced-triggers.md 23 KB
- references/best-practices.md 17 KB
- references/common-actions.md 19 KB
- references/custom-actions.md 7.3 KB
- references/expressions-and-contexts.md 16 KB
- references/modern-features.md 11 KB
- scripts/test_generator.sh 13 KB runs code
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.
- 3d ago First seen · 351 lines · 27 tokens per session scan A 485a62c648f2
github-actions-generator is a skill published in the GitHub repository akin-ozer/cc-devops-skills (303 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 2,841 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
ci-security-scanning-with-strix
Add security scanning to CI/CD with Strix — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code before it merges, with results as PR comments and SARIF uploaded to code scanning. Covers both the self-hosted open-source CLI (runs in your runner)…
dsh-web-pre-push-checks
Use before pushing, opening or updating a pull request, or claiming dsh-web checks pass. Selects the required repository gates and diff-specific generation, build, and GUI evidence.
azsdk-common-pipeline-analysis
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…
github-ci-fix
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.
ci-formats-review
Review SARIF, CodeClimate, compact, markdown, badge, and other CI-facing output formats for correctness and integrator expectations. Use when changes affect machine-consumed report formats or CI presentation layers.
deploy
Trigger the claude-desktop-extra Build & Release GitHub Actions pipeline (build-and-release.yml). With no argument the skill inspects the changes since the last release and decides forcerebuild itself; "/deploy force" / "/deploy no-force" override.