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 HybridAIOne/hybridclaw --skill code-reviewgit clone --depth 1 https://github.com/HybridAIOne/hybridclawWrote 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/hybridaione/hybridclaw/code-review)<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/code-review"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/code-review.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.00775 |
| Opus 5 | $0.00010 | $0.00387 |
| Sonnet 5 | $0.00004 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
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 8d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Use this skill to review local changes or an existing GitHub pull request for correctness, regressions, maintainability, security, and missing tests.
Review Order
- Establish scope with
git status --short,git diff --stat, andgit diff --name-only. - Read the changed files, not just the diff, before judging behavior.
- Run targeted validation when it exists: tests, typecheck, lint, build, or repo-specific checks.
- Present findings ordered by severity, then open questions, then a brief summary.
Primary Workflows
Local Branch Review
Use local git state when the change is in the current checkout:
git status --short
git diff --stat
git diff --name-only
git diff --staged
git diff <base-branch>...HEAD
git log --oneline <base-branch>..HEAD
Replace <base-branch> with the repository's actual review base branch.
GitHub PR Review
Use gh when the review target is an open pull request:
gh pr view 123
gh pr diff 123
gh pr checkout 123
gh pr view 123 --comments
After checking out the PR branch, review it the same way as a local branch and run the relevant repo checks before leaving comments.
What to Look For
Prioritize issues that change behavior or raise delivery risk:
- incorrect logic or broken edge cases
- state, data, or migration regressions
- auth, permission, or secret-handling mistakes
- missing validation, retries, or error handling
- flaky or incomplete tests
- risky coupling, hidden side effects, or cleanup gaps
Treat pure style comments as low priority unless the user explicitly asks for a style review.
Review Output
Default to this structure:
- Findings
- Open questions or assumptions
- Brief summary
For each finding:
- cite the file and the most relevant line or function
- explain the concrete failure mode or risk
- describe the user-visible impact when possible
- note the missing test or validation that would catch it
If there are no findings, say that explicitly and mention any residual risk such as unrun integration tests or unverified deployment paths.
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.
- 8d ago First seen · 118 lines · 21 tokens per session scan A 8c92f0c0aa8d
code-review is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 775 once invoked, about $0.0001 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
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
code-review
Reviews code for bugs, security issues, and best practices.
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
extending-hobby-smoke-tests
Design, extend, review, or debug PostHog Hobby end-to-end smoke tests in bin/hobby-ci.py and .github/workflows/ci-hobby.yml. Use when adding an ingestion round trip, deciding whether a product belongs in Hobby CI, changing the CI Hobby service topology or API-key scopes, or diagnosing a smoke test that captures data…
java-code-review
Review Java code for bugs, duplicate code, correctness risks, maintainability improvements, and missing tests. By default review files modified in git; when the user explicitly names files, classes, packages, or a diff, review that scope instead. Generate a detailed review.md report with actionable comments and fixes.