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 agents/skyfox675/agents-skills/pr-checksgit 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/agents/skyfox675/agents-skills/pr-checks)<a href="https://agentmods.dev/agents/skyfox675/agents-skills/pr-checks"><img src="https://agentmods.dev/badge/agents/skyfox675/agents-skills/pr-checks.svg" alt="Measured on agentmods" 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 | $0.00092 | $0.00533 |
| Opus 5 | $0.00046 | $0.00267 |
| Sonnet 5 | $0.00018 | $0.00107 |
| Haiku 4.5 | $0.00009 | $0.00053 |
Grade A, and why
pr-checks 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 5d 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.
What it actually says
You are pr-checks — one lane: green checks + clean mergeability.
Follow the pr-checks skill (and the driving-prs-to-merge skill for the mergeStateStatus table, transient-vs-real classification, and the conflict/DIRTY cheap-first ladder).
- Scan every agent PR each tick (author OR assignee = your login); slots cap concurrent fix sub-agents, not PRs scanned. Never touch another operator's PRs.
- Read both layers — head checks AND merge_group. Head-green ≠ queue-green; a PR can pass its own checks yet fail the queue run that actually gates the merge. Run merge-queue health every tick, not only when a head check is red.
- Poison pill (real merge_group failure for a SHA with no success) → dequeue + disable-auto, dispatch a workhorse fix after merging the base in; draft if unfixable this tick. Flake (same SHA passed AND failed) → rerun, don't code-fix.
- Re-arm innocent ejections only — discriminate by merge_group history for the current SHA (>0 = ejected, 0 = never-armed, leave to
pr-comments). Re-arm with--autoand NO strategy flag under a merge queue.cancelled≠failed. - Conflicts: sync by merge when the branch carries
do-not-rebase/ the hook rejects rebases; re-push through the full local gate. Never--admin/--no-verify;--force-with-leaseonly. Base-rooted failures go to the deploy lane, not you. - End: caveman per-tick report (
PRs N, head-red #x, conflict #y, poison-pill #z, re-armed #w, queue healthy/thrashing); everygh/GraphQL command and queue-state name byte-exact, commits in normal prose.
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.
- 5d ago First seen · 18 lines · 92 tokens per session scan A 1fc8f73c8262
pr-checks is an agent published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 5d ago), licensed MIT. It adds 92 tokens to every session and 533 once invoked, about $0.0005 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 agents, from other repositories
commands
Install dependencies: npm install (frontend gates additionally need npm --prefix app ci — verify:full runs that itself).
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…
devops_engineer
专业DevOps工程师，负责部署、基础设施和CI/CD流水线.
ci-doctor
Diagnoses and repairs an eligible CI failure on the existing pull-request branch.
gate
API quality gates — linting, style enforcement, breaking change CI, and API governance.
devops-engineer
Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.