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/devstride/claude-plugin/ci-auditnpx skills add devstride/claude-plugin --skill ci-auditgit clone --depth 1 https://github.com/devstride/claude-pluginWhat 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 | $0.00044 | $0.01810 |
| Opus 5 | $0.00022 | $0.00905 |
| Sonnet 5 | $0.00009 | $0.00362 |
| Haiku 4.5 | $0.00004 | $0.00181 |
Grade A, and why
ci-audit 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 yesterday.
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human output. Read ${CLAUDE_PLUGIN_ROOT}/skills/build-item/references/plain-language-output.md once per top-level run; composed skills reuse it. Apply it to every message.
Audit GitHub Actions against the loop's floor: every profile spends expensive pull-request CI once, after review and matched pre-ship checks settle on the final HEAD. Count minutes, expose early work as well as reruns, and name the repair.
Read-only. Query with gh and print a report; never cancel a run, edit a workflow, or change
a setting. Optional argument — window in days (default 7) and/or workflow name: $ARGUMENTS
Config. .claude/ds-config.json: ci.workflowGlobs,
ci.expectedRunsPerPullRequest (default 1), release.releaseSource,
release.productionBranch, and baseBranch.
Why the Actions run count lies
A push to a correctly held draft still creates an all-skipped run costing seconds. Count a run as
executed only when a job beyond the configured gate/detect job finishes other than skipped;
sum non-skipped job minutes. A run can meet the one-per-workflow count and still be waste: if it
was triggered before the final ready flip, the suite was released before review/pre-ship settlement.
1. Collect
gh api "repos/{owner}/{repo}/actions/runs?per_page=100&created=>=$(date -u -v-${DAYS}d +%Y-%m-%d 2>/dev/null || date -u -d "-${DAYS} days" +%Y-%m-%d)&status=completed" --paginate \
--jq '.workflow_runs[]|{id,event,head_sha,head_branch,head_repository:.head_repository.full_name,workflow_id,name,created_at,run_started_at,conclusion,pull_requests:(.pull_requests // [])}'
Use REST, not gh run list: pull-request associations and head repository prevent a reused branch
or same-named fork from joining two PRs. Paginate to the window start; if the API stops short,
report a floor. Resolve workflow FILES first, then filter by id — names are not unique:
gh api "repos/{owner}/{repo}/actions/workflows?per_page=100" --paginate \
--jq '.workflows[]|{id,name,path}'
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.
- yesterday First seen · 126 lines · 44 tokens per session scan A c032017aa70c
ci-audit is a skill published in the GitHub repository devstride/claude-plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 1,810 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…