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 dayfinggg/openai-codex-agent-skills --skill github-actions-changegit clone --depth 1 https://github.com/dayfinggg/openai-codex-agent-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/dayfinggg/openai-codex-agent-skills/github-actions-change)<a href="https://agentmods.dev/skills/dayfinggg/openai-codex-agent-skills/github-actions-change"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/github-actions-change/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/dayfinggg/openai-codex-agent-skills/github-actions-change"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/github-actions-change.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 | $0.00034 | $0.00368 |
| Opus 5.5 | $0.00014 | $0.00147 |
| Sonnet 5.5 | $0.00007 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
github-actions-change 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.
What it actually says
Preserve workflow coverage and trust boundaries while implementing the requested CI/CD behavior.
- Read affected workflows, local or reusable actions, scripts, runner configuration, required checks, and current failures. Determine which events and branch contexts are intentionally supported.
- Trace the origin of checked-out code, artifacts, caches, inputs, and expressions into every privileged job. Distinguish workflow code trust from permissions to trigger it.
- Preserve required events and user-access behavior. Fix untrusted interpolation or checkout without removing supported events as an incidental security shortcut.
- Inspect token permissions, secret exposure, environment restrictions, and dependency resolution. Respect an existing workflow dependency lockfile. Otherwise use supported immutable dependency references and verify their origin where the task changes them.
- Separate caches from release artifacts. Check cache keys, restore trust, build inputs, and artifact provenance. A restored cache must not silently replace the artifact associated with the tested commit.
- Validate YAML and action inputs using existing tooling, then run the relevant event path where authorized. Local YAML parsing alone does not prove GitHub event semantics.
- Inspect the actual commit's jobs, skipped paths, test counts, and outputs. If PR work must wait on checks, use the host's supported PR watcher and obey its handback contract rather than polling.
Use the current GitHub Actions secure-use reference and workflow syntax. Do not add hooks, unrelated actions, or new approval stages merely because an external guide mentions them.
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 · 18 lines · 34 tokens per session scan A 2a2b946831ef
github-actions-change is a skill published in the GitHub repository dayfinggg/openai-codex-agent-skills (8 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 368 once invoked, about $0.0001 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 2026-10-30.
Other skills, from other repositories
ship
Push, open a PR, and watch CI; land mode merges and cleans branches. Triggers "ship it", "create PR", "babysit CI", "land it", "fix CI and merge".
factory-ci
CI and pull-request review conventions. One canonical .github/workflows/ci.yml is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; anthropics/claude-code-action@v1 reviews every PR against the factory-pitfalls.md checklist as a required…
devops-specialist
A DevOps and operations guide for running software reliably. DevOps combines software development with the work of building, deploying, monitoring, and maintaining systems.
factory-deployment
Deployment and infrastructure conventions across builds. Vercel + Neon for web (with PR branch DBs), Cloud Run for Python services (one service per entry-point variant), GitHub Actions matrix-deploy on merge, Terraform with environments/modules layout for AWS / compliance customers, RDS IAM authentication for AWS DBs…
npm-trusted-publishing
Set up or debug npm Trusted Publishing (OIDC) from GitHub Actions. Handles permissions, metadata validation, and provenance.
tfx-ship
A release workflow for publishing triflux versions through GitHub Releases, the npm package registry, and the Claude Code marketplace. It also supports version changes, dry runs, skipped tests, and no-publish runs.