Borrowing it
Nothing to install: this file belongs to Szesnasty/Jarvis. 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/Szesnasty/Jarvis/main/.claude/skills/code-reviewer/SKILL.mdgit clone --depth 1 https://github.com/Szesnasty/JarvisWrote 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/szesnasty/jarvis/code-reviewer)<a href="https://agentmods.dev/skills/szesnasty/jarvis/code-reviewer"><img src="https://agentmods.dev/badge/skills/szesnasty/jarvis/code-reviewer.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 | $0.00047 | $0.00630 |
| Opus 5 | $0.00023 | $0.00315 |
| Sonnet 5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
code-reviewer 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 7d 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.
This is a copy
88% identical to code-reviewer — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
When reviewing code, follow this structured process:
1. Read First, Judge Second
Read all changed files completely before writing any feedback. Understand the intent and context before critiquing details.
2. Categorize Findings by Severity
- Critical — Security vulnerabilities, data loss risks, correctness bugs
- High — Performance issues that will bite in production, error handling gaps, race conditions
- Medium — API design issues, missing validation at system boundaries, type safety gaps
- Low — Style inconsistencies, naming, minor readability improvements
3. What to Check
Correctness
- Does the code do what it claims to do?
- Are edge cases handled (null, empty, boundary values)?
- Are error paths tested and recoverable?
Security
- Input validation at system boundaries (user input, external APIs)
- SQL injection, XSS, command injection risks
- Secrets or credentials in code
- Dependency vulnerabilities
Architecture
- Does this change belong in this module?
- Are the abstractions at the right level?
- Will this be maintainable in 6 months?
- Does it follow the existing patterns in the codebase?
Performance
- O(n²) or worse in hot paths?
- Unbounded queries or collections?
- Missing indexes on queried fields?
- Unnecessary allocations in loops?
Testing
- Are the critical paths covered?
- Do tests verify behavior, not implementation?
- Are edge cases and error paths tested?
4. How to Give Feedback
- Lead with the specific file and line
- State what the issue is, not just that there is one
- Explain WHY it matters, not just that it's wrong
- Suggest a fix when possible
- Distinguish between "must fix" and "consider changing"
5. Output Format
## Code Review: [component/feature name]
**Overall Assessment**: [Good | Needs Work | Critical Issues] — one sentence summary
### Critical Issues
[numbered list or "None found"]
### High Priority
[numbered list with file:line references]
### Medium Priority
[numbered list]
### Low Priority
[numbered list]
### Architecture Positives
[what's done well — always include this]
### Recommended Priorities
[ordered list of what to fix first]
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.
- 7d ago First seen · 95 lines · 47 tokens per session scan A db84353b0ffa
code-reviewer is a skill published in the GitHub repository Szesnasty/Jarvis (10 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 630 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to code-reviewer, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
ha-code-review
Hope-native review of uncommitted, staged, commit, branch, or PR changes: discover concrete regressions, independently verify candidates, and report actionable findings first without speculative noise.
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
codex
Delegate coding work to the OpenAI Codex CLI for repository changes, reviews, and focused fixes.
raytsystem-run-review
Independently review an raytsystem run, diff, contract, test result, or milestone checkpoint and return structured findings. Use for REVIEW, architecture/contracts/data-integrity/test critique, gate verification, or pre-promotion review; remain read-only and separate from the writer context.
raytsystem-security-review
Audit raytsystem changes for prompt injection, provenance bypass, path/symlink/hardlink escape, secret leakage, stale fencing, partial promotion, unsafe parsing, and unapproved side effects. Use for SECURITY REVIEW, adversarial testing, recovery review, or approval-boundary validation; remain independent and read-only.
code-review
Review a git diff (or working-tree changes) like a senior engineer — correctness, security, performance, readability — and return a verdict plus structured, line-anchored findings.