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.
git clone --depth 1 https://github.com/andrei-isvoran96/claude-skill-labWrote 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/commands/andrei-isvoran96/claude-skill-lab/review)<a href="https://agentmods.dev/commands/andrei-isvoran96/claude-skill-lab/review"><img src="https://agentmods.dev/badge/commands/andrei-isvoran96/claude-skill-lab/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/commands/andrei-isvoran96/claude-skill-lab/review"><img src="https://agentmods.dev/badge/commands/andrei-isvoran96/claude-skill-lab/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 | $0.00000 | $0.00568 |
| Opus 5 | $0.00000 | $0.00284 |
| Sonnet 5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade B, and why
review scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
REVIEW_HISTORY=$(cat .claude/review-history.txt) What it actually says
You have finished writing code. Now invoke a fresh, unbiased code review.
First, check if a previous review history file exists at .claude/review-history.txt. If it does, read its contents — you will include it in the reviewer prompt so previously addressed findings are not re-flagged.
Then run the following command using Bash to spawn an independent Claude reviewer. Dynamically build the prompt as follows:
- Start with the base prompt (the system instructions below)
- If review history exists, append it as a "PREVIOUSLY FLAGGED AND FIXED" section
- Pipe the git diff into the final command
REVIEW_HISTORY=""
if [ -f .claude/review-history.txt ]; then
REVIEW_HISTORY=$(cat .claude/review-history.txt)
fi
if [ -n "$REVIEW_HISTORY" ]; then
CONTEXT="
IMPORTANT — PREVIOUSLY FLAGGED AND ALREADY FIXED:
The following issues were flagged in prior reviews and have already been addressed. Do NOT re-flag these. Only report NEW issues not covered below.
${REVIEW_HISTORY}"
else
CONTEXT=""
fi
(git diff <BASE_BRANCH> -- . ':!*.lock' ':!*.lockb' | head -8000) | claude -p "You are a senior code reviewer. Review the following diff thoroughly and critically. Look for:
- Bugs and logic errors
- Security vulnerabilities
- Performance issues
- Edge cases and error handling gaps
- Code quality and readability concerns
Do NOT assume the author's intent. Only evaluate what the code actually does. Be specific — reference file names and line numbers.
If the code looks good, say so briefly. If there are issues, list them by severity (critical / warning / nitpick).
${CONTEXT}"
After the review output is returned:
-
Display it to the user in full. Do not summarize or filter the review — show it exactly as received.
-
Save a summary of the findings to
.claude/review-history.txtfor future reviews. Write ONLY the issue titles/descriptions (one per line, prefixed with severity). Do NOT include the full review text — keep it concise. Append to the existing file (don't overwrite). Example format:
=== Review 2026-04-09 ===
- [critical] SSRF bypass in thumbnail proxy — scheme not validated
- [warning] Blob URL memory leak in DriveThumbnail on unmount
- [nitpick] params: any violates no-any coding standard
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 57 lines · 0 tokens per session scan B 211a0a00db2e
review is a command published in the GitHub repository andrei-isvoran96/claude-skill-lab (1 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 568 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.