Borrowing it
Nothing to install: this file belongs to open-software-network/os-clovy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/open-software-network/os-clovy/main/.agents/skills/repo-review/SKILL.mdgit clone --depth 1 https://github.com/open-software-network/os-clovyWrote 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/open-software-network/os-clovy/repo-review)<a href="https://agentmods.dev/skills/open-software-network/os-clovy/repo-review"><img src="https://agentmods.dev/badge/skills/open-software-network/os-clovy/repo-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/open-software-network/os-clovy/repo-review"><img src="https://agentmods.dev/badge/skills/open-software-network/os-clovy/repo-review.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 | $0.00134 | $0.02533 |
| Opus 5 | $0.00067 | $0.01267 |
| Sonnet 5 | $0.00027 | $0.00507 |
| Haiku 4.5 | $0.00013 | $0.00253 |
Grade A, and why
repo-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 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo review battery
Independent review axes over git diff <fixed-point>...HEAD. Each axis is a
prompt template in axes/ and runs as its own sub-agent — or on
another harness entirely — so findings don't contaminate each other; the
caller aggregates without reranking across axes.
- Standards (axes/standards.md) — does the diff conform to this repo's documented rules?
- Spec (axes/spec.md) — does the diff faithfully implement what was asked?
- Adversarial (axes/adversarial.md) — actively try to break confidence in the change.
A change can pass one axis and fail another (right thing built wrong, wrong thing built right, correct-looking thing that fails under stress). Keeping the axes separate stops one from masking another — never merge or rerank findings across axes.
Sizing the battery
A cross-harness run costs real tokens (a single Codex axis run is roughly 150-200k). Size the battery to the diff instead of always running everything:
- Trivial (docs-only, one-liners, no runtime surface): one adversarial run, one round, cheapest harness. Skip Spec when no spec exists.
- Standard (typical feature/fix): full battery once, then converge on the adversarial axis only.
- High-stakes (auth, billing, data loss, migrations, wire contracts, or diffs a delegate/implementer harness wrote): full battery, multi-round convergence, and run the adversarial axis on both harnesses at least once — the finding sets are measurably disjoint (see CALIBRATION.md).
1. Pin the fixed point
The fixed point is whatever the user names (main, a SHA, HEAD~5). For a PR
branch it defaults to origin/main — not local main, which goes stale in
worktrees and silently widens the diff. Before spawning anything:
git fetch origin main
git rev-parse <fixed-point> # must resolve
git log <fixed-point>..HEAD --oneline
git diff <fixed-point>...HEAD --stat # must be non-empty (three-dot: merge-base)
What ships with it
8 files 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 · 203 lines · 134 tokens per session scan A 0c9e7c4444b3
repo-review is a skill published in the GitHub repository open-software-network/os-clovy (356 stars, last pushed today), licensed MIT. It adds 134 tokens to every session and 2,533 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
orbit-github
Open Orbit briefing skill — selected by the Orbit pipeline when GitHub is the user's only connected connector, or when the user explicitly scopes their daily digest to GitHub. Pulls the past 24 hours of PRs, review requests, issues, CI runs, and merges from the user's authenticated GitHub connection and renders them…
diff-review
Render the patch-edit run's accumulated changes as a reviewable diff, surface it through a GenUI choice surface, and persist the user's accept / reject decision into the artifact manifest.
review-preflight
Review tooling for a PR: review-preflight prints REVIEW.md's criteria and the PR's live gate state before a review; ci-triage maps a PR's failing checks to already-filed issues.
personal-commands
Edit hex.config.ts, not .hex-sdk. Config and installed dependencies execute with the user's normal permissions; use only trusted packages and avoid network, filesystem, environment, or subprocess access unless the requested command requires it. Run bun run check after editing.
ghx
Guidance for safe, reliable GitHub CLI workflows across issues, pull requests, and reviews.
github-pr-fix
Fix a GitHub pull request by addressing feedback or CI failures, pushing changes, and publishing replies.