kucherenko/gangsta

audit-review

Use when completing tasks, implementing major features, or before merging — dispatches the-inspector to audit the books before the job is closed

First seen Apr 17, 2026

Installation

$ npx skills add kucherenko/gangsta --skill audit-review

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from kucherenko/gangsta · top by installs.

npx skills add kucherenko/gangsta

Browse all from kucherenko/gangsta

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 80
License LICENSE
Default branch master
Open issues 1
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,303 B
  • docs SUMMARY.md 166 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 42 installs

SKILL.md

The Audit: Requesting Code Review

Overview

Dispatch the-inspector to catch issues before they compound. The inspector gets precisely crafted context for evaluation — never the session's history. This keeps the inspector focused on the work product, not the thought process, and preserves your context for continued work.

Core principle: Audit early, audit often.

When to Request

Mandatory:

  • After each task in parallel execution (The Hit)
  • After completing a major feature
  • Before merge to main

Optional but valuable:

  • When stuck (fresh perspective)
  • Before refactoring (baseline check)
  • After fixing complex bug

How to Request

1. Get Git SHAs

BASE_SHA=$(git rev-parse HEAD~1)  # or origin/main
HEAD_SHA=$(git rev-parse HEAD)

2. Dispatch the-inspector

Use the Task tool to dispatch the the-inspector agent with subagent_type: "the-inspector". Do NOT use "general" or "general-purpose" — these are not valid in a Gangsta Agents installation.

Fill the template at the-inspector-prompt.md in this skill directory with the following placeholders:

  • {WHATWASIMPLEMENTED} — What you just built
  • {PLANORREQUIREMENTS} — What it should do (Contract clause, spec section)
  • {BASE_SHA} — Starting commit
  • {HEAD_SHA} — Ending commit
  • {DESCRIPTION} — Brief summary of the changes

3. Act on Findings

Severity Action
Critical Fix immediately. Do not proceed until resolved.
Important Fix before proceeding to the next task.
Minor Note for later. Don't block progress.
Wrong Push back with technical reasoning.

Example

[Just completed implementing auth middleware]

1. Get SHAs:
   BASE_SHA=$(git log --oneline | grep "previous task" | head -1 | awk '{print $1}')
   HEAD_SHA=$(git rev-parse HEAD)

2. Dispatch the-inspector:
   WHAT_WAS_IMPLEMENTED: JWT auth middleware with role-based access
   PLAN_OR_REQUIREMENTS: Contract section 3.2 — Authentication
   BASE_SHA: a7981ec
   HEAD_SHA: 3df7661
   DESCRIPTION: Added auth middleware, role guards, token validation

3. Inspector returns:
   Strengths: Clean separation, real tests
   Issues:
     Important: Missing token expiry check
     Minor: Magic number for token TTL
   Assessment: Ready with fixes

4. Fix important issue, proceed to next task.

Integration with Heist Pipeline

  • The Hit: Audit after each Crew Lead's territory completion
  • Laundering: Final audit before the Don's approval
  • Ad-hoc work: Audit before merge

Red Flags

Never:

  • Skip audit because "it's simple"
  • Ignore Critical issues
  • Proceed with unfixed Important issues
  • Argue with valid technical feedback without evidence

If inspector is wrong:

  • Push back with technical reasoning
  • Show code/tests that prove it works
  • Use gangsta:receiving-orders for processing feedback rigorously

Omerta Compliance

  • Rule of Truth: Inspector reviews actual diffs, not claims
  • Introduction Rule: Inspector communicates through the audit skill, not directly with Workers