Kakashi Audit — Security skill for Claude Code
Full audit -- DELIBERATELY exposes original -> token mapping (only run when asked).
How to install Kakashi Audit
Installs to ~/.claude/skills/muhammadatef-kakashi-kakashi-audit/SKILL.md
mkdir -p ~/.claude/skills/muhammadatef-kakashi-kakashi-audit && curl -fsSL https://raw.githubusercontent.com/Muhammadatef/kakashi/HEAD/commands/kakashi-audit.md -o ~/.claude/skills/muhammadatef-kakashi-kakashi-audit/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Kakashi Audit does
description: Full audit -- DELIBERATELY exposes original -> token mapping (only run when asked)
Audit the file $ARGUMENTS using kakashi.
Steps
- Warn the user FIRST: "Running audit will print every original secret value alongside its masked token to this conversation. The agent (me) will see those secrets. Confirm you want to proceed."
- Only if confirmed (or the user explicitly asked for audit), run in shell:
kakashi audit "$ARGUMENTS"(fall back to `npx -y @muhammada
Alternatives in Security
- Token Scan — Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP l 3.8k ★
- Query Token Audit — Audit token security to detect scams, honeypots, and malicious contracts across BSC, Base, Solana, and Ethereu 483 ★
- Reflexion — Audit and optimize the .claude/ ecosystem — skills, hooks, guides, patterns, agents, and settings — for qualit 224 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
AI Spend
Audit Claude Code token efficiency: MCP overhead, session patterns, skill cost, cache hit rate. Add --full for
Skills Suggest
Audit recent sessions for repeated tasks and AI-output-then-manual-verification patterns. Produces a ranked li
Manifest Vault
Use when asked to optimize, clean up, audit, or improve an Obsidian vault, assess vault health, or find struct
Delegated Work Audit
Compare what a teammate or agent delivered in one or more PRs against what was asked in tickets, PR comments,
Dart Audit Code
Audit Dart/Flutter code for anti-patterns, null/late usage, magic map keys, names that should be enums, comple
Audit Milestone
Audit milestone completion against original intent before archiving
Related Agents
Audit Fix Verifier
Verifies a fix applied by audit-fix-agent actually resolves the original finding and introduces no regression.
Swe Dev Critical Systems Engineer
Audit long-lived, business-critical, regulated systems. Exposes invariants, failure modes, abstractions, and o
Fresh Reader
A deliberately process-blind final reader for finished, audit-cleared material. A WEAK PROXY for the human out