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 richfrem/agent-plugins-skills --skill authoring-github-workflowsgit clone --depth 1 https://github.com/richfrem/agent-plugins-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/richfrem/agent-plugins-skills/authoring-github-workflows)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/authoring-github-workflows"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/authoring-github-workflows/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/richfrem/agent-plugins-skills/authoring-github-workflows"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/authoring-github-workflows.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 | $0.00104 | $0.00909 |
| Opus 5.5 | $0.00042 | $0.00364 |
| Sonnet 5.5 | $0.00021 | $0.00182 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
authoring-github-workflows 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 today.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring GitHub Workflows (authoring-github-workflows)
Generates .github/workflows/*.yml CI/CD workflows and GitHub-native agent configurations (.github/agents/*.agent.md, gh-aw workflows) without hand-editing generated frontmatter.
Contents
- Constraints • Modes • Quick start • Workflow • Verification • References
Constraints
- Deterministic vs agentic: a plain Action has no runtime LLM; anything prompt-driven is an agent or gh-aw workflow.
- Least privilege: every workflow sets an explicit minimal
permissions:block andtimeout-minutes; pin third-party actions to a major version or SHA. - Secrets only via
${{ secrets.NAME }}; never hardcode or log them. - Generated frontmatter is never hand-edited: run
scaffold_github_agent.py; the gh-aw.lock.ymlcomes only fromgh aw compile. - Kill switch integrity (smart-failure agents): the phrase appears verbatim in the
.agent.mdbody and in the runner's grep condition.
Modes
| Mode | Use when | Entry point | Reference |
|---|---|---|---|
action |
Plain CI/CD workflow YAML | scripts/scaffold_github_action.py |
create-github-action.md |
agent |
Skill to Copilot agent (A), gh-aw workflow (B) or smart-failure agent (C) | scripts/scaffold_github_agent.py |
create-agentic-workflow.md |
scripts/scaffold_agentic_workflow.py is an older generator for IDE (.prompt.md, handoffs) and CI/CD agents; use it only when you need those outputs.
Quick start
python3 scripts/scaffold_github_action.py --category test --platform python --name "CI"
python3 scripts/scaffold_github_agent.py --skill-dir plugins/<plugin>/skills/<skill> --target B
Workflow
- Pick the mode and read its reference before running anything.
- Gather triggers, platform or target, engine and tools; for agents, show a recap and get confirmation.
- Run the entry point; for target B run
gh aw compile. - Validate (below). On failure follow that mode's section in fallback-tree.md.
What ships with it
17 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.
- evals/evals.json 2.1 KB
- references/acceptance-criteria.md 1.1 KB
- references/action-types.md 1.8 KB
- references/advanced-workflows.md 13 KB
- references/agent-types.md 1.8 KB
- references/fallback-tree.md 3.6 KB
- references/github-agentic-workflows.md 12 KB
- references/modes/create-agentic-workflow.md 2.9 KB
- references/modes/create-github-action.md 2.9 KB
- references/workflow-templates.md 8.0 KB
- scripts/gh_agent_templates.py 7.9 KB runs code
- scripts/scaffold_agentic_workflow.py 18 KB runs code
- scripts/scaffold_github_action.py 13 KB runs code
- scripts/scaffold_github_agent.py 13 KB runs code
- scripts/validate_github_agent.py 7.2 KB runs code
- tests/test_quickstart.py 2.7 KB runs code
- tests/test_scaffold_github_agent.py 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.
- today First seen · 63 lines · 104 tokens per session scan A a68c18fbc1f6
authoring-github-workflows is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 909 once invoked, about $0.0004 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 2026-10-24.
Other skills, from other repositories
beevibe-verify-pr
CI verification before marking a PR-bearing task done. Use BEFORE calling mcpbeevibeupdateprogress(done) on any session whose deliverable is a pull request — including the first dispatch (you opened the PR with gh pr create) and any revision dispatch (you pushed new commits to an existing PR). Watches the PR's…
ap-depth-prober
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
github-actions-supply-chain
Use when reviewing GitHub Actions workflow files for security issues, hardening CI pipelines, or assessing supply chain risk in a repository that uses GitHub Actions.
container-and-deployment
CIEL's framework for Docker containerization and CI/CD deployment strategies.
starfleet-github
GitHub PR/CI/backport interaction via starfleetctl (read-only + mutating commands, PR claims, backports). Load when checking PR status/CI, claiming a PR branch, submitting or repairing a PR, or backporting.