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 skyfox675/agents-skills --skill ci-speed-huntinggit clone --depth 1 https://github.com/skyfox675/agents-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/skyfox675/agents-skills/ci-speed-hunting)<a href="https://agentmods.dev/skills/skyfox675/agents-skills/ci-speed-hunting"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/ci-speed-hunting/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/skyfox675/agents-skills/ci-speed-hunting"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/ci-speed-hunting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00241 | $0.04572 |
| Opus 5 | $0.00120 | $0.02286 |
| Sonnet 5 | $0.00048 | $0.00914 |
| Haiku 4.5 | $0.00024 | $0.00457 |
Grade A, and why
ci-speed-hunting 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 11d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI Speed Hunting (authoritative latency-reduction method)
A serial merge queue can only drain as fast as the merge-gating critical path completes, so the wall-clock long pole is a tax on every PR in flight. Shaving minutes off the critical path raises queue throughput for the whole team — the same leverage the flake hunter gets from killing an ejecting flake, from the other direction.
This skill pairs with the ci-flake-hunting skill (which owns failures, flakes, and flake-vs-infra classification — it touches RED jobs; you touch SLOW green jobs, and the two never overlap) and builds on the merge-queue mechanics in the driving-prs-to-merge skill. Where a "just make it faster" instinct conflicts with this skill's coverage-is-sacred rule, this skill wins.
Project bindings
Project-agnostic; the adopting project defines these (the full set lives in driving-prs-to-merge). Used here:
| Placeholder | Meaning |
|---|---|
<owner>/<repo> |
GitHub repository slug |
<integration-branch> |
Branch PRs target and the queue merges into |
<ci-workflow> |
The per-PR CI workflow file that gates merge (e.g. pr-checks.yml) |
<summary-check> |
The rollup check whose completion the critical path ends at |
<e2e-suite> |
The end-to-end / browser test job or matrix (often the long pole) |
<merge-strategy> |
Allowed strategy flag — and whether a merge queue governs the branch |
The one rule
Coverage is sacred. Speed never costs verification. You make CI faster by doing the same work faster (caching, parallelism, right-sized runners, build-once) or by skipping work that provably cannot affect the diff (a correct changed-paths tier). You NEVER make it faster by checking less: no deleted test, no test.skip, no narrowed --grep, no shard with fewer specs, no gate pulled from the summary check's needs:, no loosened assertion, no timeout-minutes cut so low it kills a legitimately slow run. If a change saves time by checking less, it is out of bounds — that is regressing coverage, not speeding CI.
What ships with it
1 file 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.
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.
- 11d ago First seen · 210 lines · 241 tokens per session scan A 47ba47cf6a0e
ci-speed-hunting is a skill published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 11d ago), licensed MIT. It adds 241 tokens to every session and 4,572 once invoked, about $0.0012 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
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
smoke-test
Health smoke tests + auto-fix for gbrain installs (and OpenClaw services when present). Run after machine/container restarts or whenever something seems broken. Tests critical services, auto-fixes bounded local issues, and reports worker topology without starting daemons. Extensible via user-defined test scripts in…
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
debug-task
Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time when it should be cached, or when outputs are empty or missing after a…
operating-github-ci-fixer
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-triage
Classify CI failures — distinguish clear regressions from infra flakes and security-test failures. Produces structured failure reports.