Skip to content
Agentmart
Submit a tool

audit-code-health

Scans codebases for security vulnerabilities, bugs, and code health issues.

Skill by vercel

IndexedMIT
Write a review

Chalk Labs

Need help deploying audit-code-health?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/kyzooghost-audit-code-health

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Scans codebases for security vulnerabilities, bugs, and code health issues. Creates structured work items for remediation. Triggers on "audit", "code review", "security scan", "find bugs", "tech debt", or "assess code quality".

Use cases: security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/audit-code-health

What's inside

Skill name
audit-code-health
Description
Scans codebases for security vulnerabilities, bugs, and code health issues. Creates structured work items for remediation. Triggers on "audit", "code review", "security scan", "find bugs", "tech debt", or "assess code quality".
License
MIT
Metadata
author: vercel · version: 1.1.0
Instructions
186 lines in SKILL.md · view on GitHub

Files (9)

  • AGENTS.md
  • README.md
  • SKILL.md
  • metadata.json
  • beads-format.md · reference/
  • bugs-checklist.md · reference/
  • code-health.md · reference/
  • examples.md · reference/
  • security-issues.md · reference/

SKILL.md (first lines)

# Code Health Auditor

Systematic audit process that scans directories to identify security issues, bugs, and code health problems. Findings are tracked as work items for remediation.

## Quick Start

Example: `For @native-yield-operations/automation-service/ do /audit-code-health`

1. **Scan** the target directory for issues
2. **Document** findings in a table (Security → Bugs → Code Health)
3. **File** work items or create a findings summary

For deeper audits, follow the [Workflow](#workflow-overview) below.

## When to Apply

Use this skill when:

- Auditing a codebase for security vulnerabilities
- Identifying bugs and edge cases
- Assessing technical debt and code health
- Creating structured work items for remediation
- Running systematic code reviews

## When NOT to Apply

Do not use this skill when:

- Developing a new feature
- Writing a new test

## Core Principles

1. **Audit only, no fixes**: Discover and document—never modify code
2. **Track everything**: All findings become work items
3. **Scoped analysis**: Stay within the target directory unless context requires external references
4. **Prioritize by impact**: Security → Bugs → Code Health

## Audit Categories by Priority

| Priority | Category    | Severity | Reference                                          |
| -------- | ----------- | -------- | -------------------------------------------------- |
| 1        | Security    | CRITICAL | [security-issues.md](reference/security-issues.md) |
| 2        | Bugs        | HIGH     | [bugs-checklist.md](reference/bugs-checklist.md)   |
| 3        | Code Health | MEDIUM   | [code-health.md](reference/code-health.md)         |

## Quick Reference

### Security Issues (CRITICAL)

- Auth/authz errors
- Injection risks (SQL, command, XSS)
- SSRF, path traversal
- Secrets or insecure defaults
- Broken crypto usage
- Missing input validation
- Dependency vulnerabilities

### Bugs (HIGH)

- Edge cases and boundary conditions
- Concurrency / race conditions
- Error handling gaps
- Resource leaks
- Numeric overflow/underflow
- Retry / timeout bugs

### Code Health (MEDIUM)

- Oversized or high-complexity modules
- Low test coverage near critical logic
- Duplicated abstractions
- Dead code or unused exports
- Poor documentation
- Misleading names

## Related Skills

- **Smart Contracts**: If you detect `*.sol` files, use the `developing-smart-contracts` skill for Solidity-specific security patterns
- **Unit Testing**: Use the `unit-testing-guidelines` skill to assess test quality and coverage gaps

## Workflow Overview

Audits run in cycles. Choose depth based on scope:

| Scope          | Cycles | When to Use                            |
| -------------- | ------ | -------------------------------------- |
| Quick scan     | 1-2    | Small PRs, single files, targeted review |
| Standard audit | 3-5    | Feature modules, API surfaces          |
| Deep audit     | 6-10   | Full codebase, security-critical systems |

Each cycle follows: **SCAN → FINDINGS → VERIFY → FILE → TRIAGE**

## Cycle Process

For each cycle, execute these steps:

```
Cycle Progress:
- [ ] Step 1: SCAN - Inspect target directory
- [ ] Step 2: FINDINGS - Document issues by category
- [ ] Step 3: VERIFY - Validate findings before filing
- [ ] Step 4: FILE - Create work items
- [ ] Step 5: TRIAGE - Assign priorities
```

### Step 1: SCAN

Analyze the target directory:

- Review code for security issues, bugs, and health problems
- Run read-only tooling: build, tests, lint, typecheck
- Use `code-simplifier` on hotspots (if available)

### Step 2: FINDINGS

Produce a findings table grouped by Security, Bugs, Code Health:

| Severity | Type     | File(s)       | Description        | Confidence |

From kyzooghost/skills, MIT.

More from kyzooghost/skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Feb 16, 2026 (8 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.1.0
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from vercel

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get audit-code-health running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying audit-code-health?

CallGet help
Cite this page

audit-code-health skill. Agent Mart. https://agentmart.dev/skills/kyzooghost-audit-code-health (last updated 2026-10-24)