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 olgaiv39/claude-oss-skills --skill public-code-reviewgit clone --depth 1 https://github.com/olgaiv39/claude-oss-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/olgaiv39/claude-oss-skills/public-code-review)<a href="https://agentmods.dev/skills/olgaiv39/claude-oss-skills/public-code-review"><img src="https://agentmods.dev/badge/skills/olgaiv39/claude-oss-skills/public-code-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/olgaiv39/claude-oss-skills/public-code-review"><img src="https://agentmods.dev/badge/skills/olgaiv39/claude-oss-skills/public-code-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00064 | $0.01024 |
| Opus 5 | $0.00032 | $0.00512 |
| Sonnet 5 | $0.00013 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
public-code-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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
public-code-review
Review the current diff, or a clearly specified set of files, as public open-source code. Report findings; do not fix anything unless the user explicitly asks.
Activate when
- Code is about to be published or merged to a public repository
- A diff needs a safety and quality pass before release
- An external contribution needs review before acceptance
Do not activate when
- A test or build is failing and needs a fix -> use
test-and-debug - The change has not been implemented yet -> use
implement-minimal - The task is packaging and shipping a release -> use
release-deploy
Required inputs
- The diff to review, or an explicit list of files
- Whether the target repository is already public
- The project's stated license
Low-resource policy
Read the first of these that exists, then follow it:
${CLAUDE_PROJECT_DIR}/.claude/shared/LOW_RESOURCE.md$HOME/.claude/shared/LOW_RESOURCE.md
If neither exists, apply this fallback: run one expensive command at a time, prefer the narrowest validation, disable watch mode, reuse existing environments, and run full validation only at a milestone boundary. Do not scan the whole filesystem to locate the policy.
Context-efficiency policy
Read the first of these that exists, then follow it:
${CLAUDE_PROJECT_DIR}/.claude/shared/CONTEXT_EFFICIENCY.md$HOME/.claude/shared/CONTEXT_EFFICIENCY.md
If neither exists, apply this fallback: select files before reading; use targeted searches and bounded ranges; do not preload references; do not reread unchanged files; finish one atomic increment and stop; create a compact handoff before context is exhausted.
Facts that must not be assumed
- That the diff is the whole change; confirm the scope under review
- That secrets scanning tooling is installed
- That README claims match current behavior
- That copied code is licensed for redistribution
Preflight
git status --shortandgit diff --statto bound the review scope- Confirm whether the review is the working diff, a staged diff, or a file list
- Read the license so compatibility findings are accurate
What ships with it
4 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 · 125 lines · 64 tokens per session scan A 0fd9c318f9c6
public-code-review is a skill published in the GitHub repository olgaiv39/claude-oss-skills (12 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,024 once invoked, about $0.0003 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
agentplane-task-closure-recovery
Use when Agentplane task completion, direct finish, branchpr integration, hosted-close, close-tail PRs, PR metadata, dirty task artifacts, or remote branch divergence need diagnosis or recovery.
reviewing-code-quality
Reviews a diff or module for slipping standards, favoring deletion over rearranging, and ends in one honest verdict. Use when a change risks oversized files, needless layers, feature logic leaking into shared code, or clever indirection. Do not use for a trivial obvious edit, or for a check that is only about whether…
review-deep
Drive the deep-review phase of an automated PR review. Consumes the walkthrough, runs the deterministic deep-review workflow (parallel lenses → adversarial validation → code-enforced threshold/caps), drafts the surviving findings, and completes the review run.
review-orchestrator
Drive an automated PR review. Produces a structured walkthrough plus inline draft comments via the octomux review CLI. NEVER posts to GitHub directly — publishing is human-gated.
audit
Use for PACEflow internal full audit: run five independent review agents, verify evidence from code/tests/logs, de-duplicate findings, and produce a severity-ranked report for release gates or comprehensive code review.
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.