Forensify

Forensify is a Quality skill for Claude Code, published by alexgreensh in repo-forensics.

170 stars26 forkson alexgreensh/repo-forensicsAdded 2026/09/07+1% in starsRepository updated 2026/09/06

agent-securityagent-skillagent-skillsai-agent-securityclaude-codeclaude-skillscodexdeveloper-toolsforensicsmcp-securityopenclaw-skillspluginssecuritysecurity-auditsecurity-scannersecurity-toolsstatic-analysissupply-chain-security

Install in seconds

Install Forensify

Copy Forensify into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/alexgreensh/repo-forensics/tree/main/skills/forensify ~/.claude/skills/forensify

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/alexgreensh/repo-forensics.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/forensify/SKILL.md in alexgreensh/repo-forensics
Installs to: ~/.claude/skills/forensify
Collection: One of 6 skills cataloged from this repository
Category: Quality — 1817 skills

What Forensify does

Forensify audits installed AI-agent stacks across Claude Code, Codex, OpenClaw, and NanoClaw. It inventories skills, MCP servers, hooks, plugins, commands, credentials, and memory files for cross-tool security risks.

Forensify is cataloged under Quality on DirSkills. Forensify comes from a repository tagged agent-security, agent-skill, agent-skills, ai-agent-security and claude-code.

Documentation

README

Excerpt

Forensify

The agent stack you have already installed is your biggest blind spot. repo-forensics catches threats before install. Forensify tells you what is already on this machine, across every agent framework, and where the credential, injection, and auto-execution surfaces are right now.

What makes this different

Every Codex user has ~/.codex/auth.json. TruffleHog will tell you it contains secrets. Forensify tells you its permissions are 0o644 (world-readable), its auth_mode is apiKey (non-rotating, broad-scope), it has not been refreshed in 47 days, AND OpenClaw's models status command is known to silently overwrite it (openai/codex#54506). That cross-ecosystem stack interaction finding is a class no existing credential scanner produces.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Forensify

What else does alexgreensh publish alongside Forensify?
Forensify is one of 6 skills that DirSkills catalogs from alexgreensh/repo-forensics, the repository it ships in. Its siblings there include Clean Skill, Code Review and Daily Helper. Each one is a separate skill with its own page in this directory, installs the same way Forensify does, and is maintained by alexgreensh in that same repository. The rest of the collection is listed on the alexgreensh/repo-forensics page.
How does Forensify compare to other Quality skills?
Forensify ranks #1737 by stars among the 1817 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Forensify against them. Open each page to compare what they document and how they install.