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 yarlson/yarstack --skill ci-reviewgit clone --depth 1 https://github.com/yarlson/yarstackWrote 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/yarlson/yarstack/ci-review)<a href="https://agentmods.dev/skills/yarlson/yarstack/ci-review"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/ci-review/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/yarlson/yarstack/ci-review"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/ci-review.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 | $0.00050 | $0.00477 |
| Opus 5.5 | $0.00020 | $0.00191 |
| Sonnet 5.5 | $0.00010 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
ci-review 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 7d 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI Review
Show which CI components protect a real contract, and which are stale, redundant, unsafe, or ineffective.
Workflow
- Confirm the repository, the comparison target if there is one, the supported platforms, and the checks required for merge.
- Map the triggers, jobs, called commands, environments, token permissions, secrets, caches, artifacts, release paths, deployment paths, and required checks. Note each trigger that runs code from forks or untrusted contributors, and the secrets and permissions that code receives.
- For each component, name its consumer and the contract it enforces. Read the repository, and, when the host allows it, bounded read-only run history such as
gh run list --workflow <file> --limit 20, to see whether a check actually runs, fails, or is skipped. - Look for duplicated logic, mismatched tool versions, path filters that skip required checks, unused matrix entries, ignored results such as
continue-on-erroror|| true, retries that hide flaky tests, dead paths, permissions broader than the job needs, third-party actions referenced by a mutable tag or branch, and caches or artifacts that nothing reads. - Classify each actionable item as
keep,simplify,merge,fix,remove, orowner decision. - Delegate tool provenance to
dependency-review, exploit paths tosecurity-review, infrastructure semantics toinfra-review, runtime readiness torollout-readiness-review, and test sufficiency totest-gap-review.
Do not edit workflows, rerun jobs, or change repository settings. Do not remove a safety gate on speculation, recommend scanners for appearance, or propose a broad rewrite.
Result
For each finding, report the location, the affected contract, the evidence, the consequence, the recommended disposition, the risk of making the change, and how to verify it. Order findings by consequence. State the scope, the evidence limits, and the smallest sequence of cleanup steps, or state that nothing is actionable. Recommendations do not authorize implementation.
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.
- 7d ago Changed 64a665447721
- 1mo ago First seen · 24 lines · 50 tokens per session scan A b0bd8741146d
ci-review is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 477 once invoked, about $0.0002 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
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.
aster-review-ci
Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.
gemini-review
Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration.
operating-infra
Author, inspect, troubleshoot, review, and apply (after explicit confirmation) infrastructure across IaC, Kubernetes, cloud resources, containers, CI/CD, and Linux hosts. Use when changing Terraform/OpenTofu, Kubernetes, Helm, Kustomize, Dockerfiles, GitHub Actions workflow/job/permissions semantics, AWS, GCP, Cloud…
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…
capture
Capture an engineering decision into Hunch's graph via a grilling interview (topic, rationale, rejected alternatives).