os-clovy: Skill for Codex

.agents/skills/repo-review/SKILL.md

repo-review is a skill for Codex from open-software-network/os-clovy. It costs 134 tokens per session (2,533 once invoked), scanned A, original, MIT.

A review process for code changes that compares the current Git diff with a chosen earlier point. It checks both the repository's documented standards and whether the change matches its original request, then probes its assumptions for failures.

In plain words
What is it for?
Reviewing trivial or substantial changes, running standards, specification, and adversarial checks as appropriate, and collecting findings from independent reviewers.
Why use it?
It separates different kinds of review problems so a change that looks correct in one respect does not hide issues in another.

Skill for Codex

Written for Codex: runs codex exec. Also seen: mentions subagents; mentions Claude Code; installed under .agents/ (shared by several agents).

This is open-software-network/os-clovy's own configuration. It tells Codex how to work on os-clovy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything os-clovy configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/open-software-network/os-clovy/main/.agents/skills/repo-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/open-software-network/os-clovy

Made for: Codex.

Wrote 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.

agentmods badge for repo-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-software-network/os-clovy/repo-review/github.svg)](https://agentmods.dev/skills/open-software-network/os-clovy/repo-review)
Your own site
<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.

agentmods 80×15 button for repo-review

Your own site · 80×15
<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>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,533 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 0c9e7c4444b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/fill-prompt.sh, scripts/run-claude.sh, scripts/run-codex.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/repo-review/SKILL.md · 203 lines

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)

Read the full file on GitHub · 203 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 203 lines · 134 tokens per session scan A 0c9e7c4444b3

Subscribe to this mod's changes

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.