AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Nit

skill-koolamusic-claudefiles-nit · by koolamusic

Adversarial bug finding using 3 isolated agents (Hunter, Skeptic, Referee) to find and verify real bugs with high fidelity. Based on bug-hunt by danpeg (https://github.com/danpeg/bug-hunt).

No reviews yet
0 installs
28 views
0.0% view→install

Install

$ agentstack add skill-koolamusic-claudefiles-nit

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-koolamusic-claudefiles-nit)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Nit? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Nit - Adversarial Bug Finding

Run a 3-agent adversarial nit hunt on your codebase. Each agent runs in isolation.

Target

The scan target is: $ARGUMENTS

If no target was specified, scan the current working directory.

Triage (Nit Ignore)

Nit respects a project-level ignore file at .claude/nitignore.md. This file tracks:

  • intentional — findings that are by design (won't fix)
  • remediated — findings that have already been fixed

Entries use a rule field formatted as category::description (e.g. security::hardcoded-token). Nit matches on file + rule to skip known findings.

A template is available at ${CLAUDE_SKILL_DIR}/references/nitignore-template.md.

Execution Steps

You MUST follow these steps in exact order. Each agent runs as a separate subagent via the Agent tool to ensure context isolation.

Step 1: Read the prompt files and check for ignore list

Read these files using the skill directory variable:

  • ${CLAUDESKILLDIR}/prompts/hunter.md
  • ${CLAUDESKILLDIR}/prompts/skeptic.md
  • ${CLAUDESKILLDIR}/prompts/referee.md

Also check if .claude/nitignore.md exists in the project root. If it does, read it and pass the ignore entries to each agent so they can skip already-triaged findings.

Step 2: Run the Hunter Agent

Launch a general-purpose subagent with the hunter prompt. Include the scan target in the agent's task. The Hunter must use tools (Read, Glob, Grep) to examine the actual code.

Wait for the Hunter to complete and capture its full output.

Step 2b: Check for findings

If the Hunter reported TOTAL FINDINGS: 0, skip Steps 3-4 and go directly to Step 5 with a clean report. No need to run Skeptic and Referee on zero findings.

Step 3: Run the Skeptic Agent

Launch a NEW general-purpose subagent with the skeptic prompt. Inject the Hunter's structured bug list (BUG-IDs, files, lines, claims, evidence, severity, points). Do NOT include any narrative or methodology text outside the structured findings.

The Skeptic must independently read the code to verify each claim.

Wait for the Skeptic to complete and capture its full output.

Step 4: Run the Referee Agent

Launch a NEW general-purpose subagent with the referee prompt. Inject BOTH:

  • The Hunter's full bug report
  • The Skeptic's full challenge report

The Referee must independently read the code to make final judgments.

Wait for the Referee to complete and capture its full output.

Step 5: Present the Nit Report

Display the Referee's final verified nit report to the user. Include:

  1. The summary stats
  2. The confirmed bugs table (sorted by severity)
  3. Low-confidence items flagged for manual review
  4. A collapsed section with dismissed bugs (for transparency)
  5. Triage-ready entries (see below)

If zero bugs were confirmed, say so clearly — a clean report is a good result.

Step 6: Offer Triage

After presenting findings, offer the user the option to triage. For each confirmed bug, output a pre-formatted ignore entry the user can approve:

| intentional | category::description | file/path | line(s) | [user adds rationale] |

Ask: "Would you like to dismiss any of these as intentional, or mark any as remediated? I can update .claude/nitignore.md for you."

If the user selects entries to triage:

  1. If .claude/nitignore.md doesn't exist, create it from ${CLAUDE_SKILL_DIR}/references/nitignore-template.md
  2. Append the selected entries to the table
  3. Confirm what was added

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.