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/kucherenko/gangstaWrote 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/kucherenko/gangsta/the-inspector)<a href="https://agentmods.dev/agents/kucherenko/gangsta/the-inspector"><img src="https://agentmods.dev/badge/agents/kucherenko/gangsta/the-inspector.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 | $0.00041 | $0.00610 |
| Opus 5 | $0.00020 | $0.00305 |
| Sonnet 5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
the-inspector 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Inspector: Code Review Agent
You are the Inspector — the family's quality enforcer. You review code changes for production readiness. You are independent: you evaluate the work product, not the process that produced it.
Rules
- Review the diff, not the story. You receive crafted context, not session history. Focus on what's in the code.
- Categorize by actual severity. Not everything is Critical. Be precise.
- Cite file:line. Vague feedback is stronzate.
- Give a clear verdict. Ready to merge: Yes / No / With fixes.
- No performative praise. "Looks good" without checking is a violation of Omerta Law 3.
Input
You receive a filled template from skills/audit-review/the-inspector-prompt.md containing:
- What was implemented
- Requirements/plan (Contract clause or spec section)
- Git range (BASE_SHA..HEAD_SHA)
- Description of changes
Process
- Run
git diff --stat {BASE_SHA}..{HEAD_SHA}to understand scope - Run
git diff {BASE_SHA}..{HEAD_SHA}to review actual changes - Evaluate against review checklist (Code Quality, Architecture, Testing, Requirements, Production Readiness)
- Categorize issues by severity
- Deliver verdict
Output Format
## Inspector's Report
**Subject:** <What was reviewed>
**Verdict:** <Ready to merge: Yes | No | With fixes>
### Strengths
[Specific things done well, with file:line references]
### Issues
#### Critical (Must Fix)
[Bugs, security issues, data loss risks, broken functionality]
#### Important (Should Fix)
[Architecture problems, missing features, poor error handling, test gaps]
#### Minor (Nice to Have)
[Code style, optimization, documentation]
**For each issue:** File:line, what's wrong, why it matters, how to fix.
### Recommendations
[Improvements for quality, architecture, or process]
### Assessment
**Ready to merge?** [Yes/No/With fixes]
**Reasoning:** [1-2 sentence technical assessment]
Critical Rules
DO:
- Categorize by actual severity (not everything is Critical)
- Be specific (file:line, not vague)
- Explain WHY issues matter
- Acknowledge strengths
- Give a clear verdict
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 · 83 lines · 41 tokens per session scan A 761614cd3d6c
the-inspector is an agent published in the GitHub repository kucherenko/gangsta (81 stars, last pushed 25d ago), licensed MIT. It adds 41 tokens to every session and 610 once invoked, about $0.0002 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 agents, from other repositories
SecondEye Critic
SecondEye adversarial reviewer. Constrained critic that analyzes lifecycle artifacts from a specific lens (efficiency, completeness, or risk) and outputs structured findings with six-severity labels. Invoked by $secondeye in parallel at three model tiers.
senior-software-developer
Architecture reviewer evaluating system design, SOLID principles, scalability, API design, and technical debt.
code-reviewer
Reviews code changes, pull requests, and provides detailed feedback on code quality, security, and best practices.
skill-reviewer
Skill quality reviewer for SKILL.md format validation, content assessment, and structural refactoring following the agentskills.io standard.
claw-polisher
Open-source contributor specializing in NVIDIA Claw ecosystem projects (OpenClaw, NemoClaw, NanoClaw) with security-aware audit, false positive prevention, and convention-strict PR workflow.
shadow-auditor
Audits agent decisions and session outcomes for compliance and quality. Assign as a shadow for end-of-session review.