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 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/skills/skyfox675/agents-skills/pr-checks)<a href="https://agentmods.dev/skills/skyfox675/agents-skills/pr-checks"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/pr-checks/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/pr-checks"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/pr-checks.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 | $0.00159 | $0.03542 |
| Opus 5 | $0.00079 | $0.01771 |
| Sonnet 5 | $0.00032 | $0.00708 |
| Haiku 4.5 | $0.00016 | $0.00354 |
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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Checks Watcher
One job: green checks + clean mergeability. Find failing CI, merge conflicts, and merge-queue failures on open agent PRs and get them fixed. Nothing else.
The critical insight this lane exists for: head-green does NOT mean queue-green. A PR can pass its own head checks (against an older base) yet fail the merge_group run that actually gates the merge. Reading only statusCheckRollup is blind to that whole class of failure — and that blindness is exactly how one poison-pill PR stalls the queue for hours.
This skill builds on the shared PR mechanics in driving-prs-to-merge (the mergeStateStatus table, CI transient-vs-real classification, the conflict/DIRTY cheap-first ladder, merge-queue operations, force-push discipline). It adds the single-lane watcher loop and the full merge-queue health protocol on top.
Project bindings
Project-agnostic; the adopting project defines these in its own CLAUDE.md (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 |
<required-checks> |
Names of the merge-gating CI checks (the rollup check and its inputs) and the workflow that runs them |
<local-gate> |
The full local verification command CI mirrors (lint + typecheck + tests) |
<merge-strategy> |
Allowed strategy flag — and whether a merge queue governs <integration-branch> |
<flake-ledger> |
Where known-flaky jobs are tracked; absent → degrade to "retry twice on same SHA" |
The watcher model
A single-lane, interval-driven loop — one concern, scanned end-to-end every tick (/loop <interval> start). Distinct from the N-slot event loop in orchestrating-slots and the one-shot pr-rescuer. One watcher per lane; lanes do not cross.
Slots = max fix sub-agents running at once — NOT a cap on PRs scanned. Scan EVERY agent PR each tick; if more PRs are red/conflicting than you have slots, queue the rest for next tick — never leave a red PR unwatched. Small fixed default (≈2 for this lane), tuned to the machine; a slots=N token in the start prompt overrides.
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.
- 5d ago First seen · 138 lines · 159 tokens per session scan A 8df64af3b919
pr-checks is a skill published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 8d ago), licensed MIT. It adds 159 tokens to every session and 3,542 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.