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 HumanDealer/vibeproof --skill code-reviewgit clone --depth 1 https://github.com/HumanDealer/vibeproofWrote 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/humandealer/vibeproof/code-review)<a href="https://agentmods.dev/skills/humandealer/vibeproof/code-review"><img src="https://agentmods.dev/badge/skills/humandealer/vibeproof/code-review.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00457 |
| Opus 5 | $0.00012 | $0.00229 |
| Sonnet 5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00046 |
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.
What it actually says
Code Review
Review a diff the way a careful senior would — looking for what will break in production, not just style. Be specific: cite file and line, explain the failure, propose the fix.
When to use
Before merging any non-trivial PR, or when the human asks to "review this", "check my diff", or "is this safe to merge".
What to review
Run git diff origin/main...HEAD (or the PR diff) and check each dimension:
1. Correctness
- Edge cases: empty input, null, zero, very large values, unicode.
- Off-by-one, boundary conditions, loop termination.
- Error handling: are failures caught and surfaced, or swallowed?
- Does the change actually do what the PR says?
2. Safety
- Secrets: nothing sensitive in the diff (rules/security-and-secrets.md).
- Injection: untrusted input concatenated into SQL / shell / HTML?
- Trust boundaries: is external/user data validated before use?
- Permissions: least privilege respected?
3. Side effects & data
- Does a conditional path have an unexpected write / delete / external call?
- Any irreversible operation (drop, overwrite, mass update) without a guard?
- Migration / schema change that's not backward compatible?
4. Simplicity & reuse
- Is there a simpler way that's just as correct?
- Duplicated logic that should be shared?
- Dead code, leftover debug prints, commented-out blocks?
5. Tests
- Does the change have tests? Do they cover the failure modes, not just happy path? Did they actually run and pass?
Output
For each finding: severity (blocker / should-fix / nit), location
(file:line), what's wrong, suggested fix. End with a clear verdict:
ready to merge or needs changes.
Default to caution on anything touching auth, money, data deletion, or external side effects.
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 · 55 lines · 24 tokens per session scan A db1616e50aa2
code-review is a skill published in the GitHub repository HumanDealer/vibeproof (2 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 457 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 2026-08-31.
Other skills, from other repositories
Code Review Excellence
Master code review best practices with constructive feedback patterns, quality assurance standards, review checklists, security considerations, and collaborative improvement techniques for high-quality software delivery.
template-comprehensive-assessment
Full checkout audit for the Research Project Template — tests, architecture, docs, manuscript, pipeline. USE WHEN user asks for comprehensive assessment, full repo review, health check across projects, audit everything, or pre-merge sanity sweep for template exemplars — even without naming docs/prompts or a skill. Not…
Code Review Checklist
Runs a systematic checklist review on any code diff or file, covering correctness, security, performance, and readability.
shipjaw-challenge
Optional full adversarial ritual for locking a Shipjaw phase plan, ADR, or tech/product decision — durable challenge-report.md via proposer vs challenger (prefer a separate subagent). Use when the user runs /shipjaw-challenge, challenge this plan, wants a written challenge report, locking a meaty phase, contester ce…
review
Review PR and build output for quality, security, and compliance. Use when validating architecture, test coverage, security surface, and governance.
code-quality
Validate code quality, formatting, and maintainability. Use when running linters, formatters, and checking naming conventions and directory structure.