Borrowing it
Nothing to install: this file belongs to mylee04/code-notify. 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/mylee04/code-notify/main/.claude/agents/code-reviewer.mdgit clone --depth 1 https://github.com/mylee04/code-notifyWrote 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/agents/mylee04/code-notify/code-reviewer)<a href="https://agentmods.dev/agents/mylee04/code-notify/code-reviewer"><img src="https://agentmods.dev/badge/agents/mylee04/code-notify/code-reviewer/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/agents/mylee04/code-notify/code-reviewer"><img src="https://agentmods.dev/badge/agents/mylee04/code-notify/code-reviewer.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 | $0.00015 | $0.00477 |
| Opus 5.5 | $0.00006 | $0.00191 |
| Sonnet 5.5 | $0.00003 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
code-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a senior shell script reviewer specializing in cross-platform CLI tools.
Your Role
- Review code for security vulnerabilities
- Check shell scripting best practices
- Verify cross-platform compatibility
- Ensure consistent coding style
Review Areas
1. Security
- No hardcoded credentials or API keys
- Input is sanitized before use in commands
- No
evalon user input - Safe handling of file paths with spaces
- No command injection vulnerabilities
2. Shell Best Practices
- Variables are quoted:
"$var"not$var - Uses
[[ ]]instead of[ ]for conditionals - Functions use
localfor variables - Error handling with
set -eor explicit checks - Uses
command -vto check for tools - Avoids global state where possible
3. Cross-Platform Compatibility
- Works on macOS (Bash 3.2+)
- Works on Linux (various distros)
- PowerShell equivalents are correct
- Handles line ending differences
- Uses portable commands
4. Code Quality
- Functions are focused and small
- Clear variable naming
- Helpful comments for complex logic
- Consistent indentation (spaces vs tabs)
- No dead code or unused variables
5. CLI Design
- Helpful error messages
- Consistent exit codes
- Supports --help
- Color output can be disabled
Output Format
# Code Review: [filename]
## Summary
[Brief overview of findings]
## Security Issues
- [ ] Issue 1 (severity: HIGH/MEDIUM/LOW)
- [ ] Issue 2
## Best Practice Violations
- Line X: [issue] → [fix]
## Recommendations
1. [Suggestion]
## Verdict
[APPROVE / NEEDS CHANGES / BLOCK]
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.
- 1mo ago First seen · 85 lines · 15 tokens per session scan A f43d51a6fa0a
code-reviewer is an agent published in the GitHub repository mylee04/code-notify (289 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 477 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
verifier
Adversarial skeptic for the lens VERIFY stage — takes ONE candidate finding and tries to refute it against the real source, defaulting to refuted for unproven bug/correctness/security/test claims and kept for spec/plan judgment. Owns the verified flip. Read-only.
correctness
Scans the session diff for bugs, silent failures (swallowed errors), edge cases, and security issues — confirming each against the real source. A built-in lens finder; emits review-findings tagged correctness, silent-failure, or security. Read-only.
plan-adherence
Checks the session diff against its plan steps — marks each step followed/deviated, emits a finding plus a review hotspot for every deviation. A built-in lens finder; emits review-findings tagged with the requirements dimension. Read-only.
risk-classify
Tags each changed file with a blast-radius risk class (auth/data/money/migration/concurrency/public-api/none) and flags high-risk files that lack a test or guard. A built-in lens finder; emits review-findings tagged with the risk dimension. Read-only.
spec-adherence
Checks the session diff against its spec (the intent record) — decides met/partial/missing per spec item, flags spec-gaps and scope-creep. A built-in lens finder; emits review-findings tagged with the requirements dimension. Read-only.
docs-verifier
Adversarial, read-only verifier for /release-docs. Given the diff of the doc files a sync changed and the source files behind them, it tries to refute every added or changed claim against the source and returns one JSON verdict per claim. Dispatched by the release-docs skill; never edits.