Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Forensify — Cross-Agent Stack Self-Audit

Read-only audit of the skills, MCP servers, hooks, plugins and credential metadata already installed on your machine, with a structured risk briefing.

Security & ReviewIntermediate★ 154⑂ 22AI score 9/10Last updated: Aug 8, 2026

What it does

  • Auto-detects installed agent ecosystems (Claude Code, Codex, OpenClaw, NanoClaw) and inventories every surface: skills, MCP servers, hooks, plugins, slash commands, memory files (CLAUDE.md, AGENTS.md, SOUL.md), and credential files.
  • Runs three stages: a zero-LLM deterministic inventory (scripts/build_inventory.py), six parallel risk-domain analyses, and a synthesis pass with grounding checks plus suppression detection, emitting briefing.md + briefing.json.
  • Never reads credential values — only file mode, permissions, auth_mode, token staleness — and surfaces cross-ecosystem interaction risks (e.g. the known bug where OpenClaw overwrites Codex OAuth tokens).
  • Hardened by design: scanned file contents are treated as hostile DATA, strings are NFKC-normalized, bidi overrides rejected, symlinks resolved via realpath, and writes are confined to the run cache folder.

Who it's for

  • Anyone who has accumulated skills, plugins and MCP servers over months and has lost track of their attack surface.
  • Users running Claude Code alongside Codex/OpenClaw who have hit config collisions or token clobbering.
  • Security-minded users who want a post-install check after adding new skills or plugins.

Examples

  1. forensify — auto-detect all ecosystems and produce a full risk briefing.
  2. forensify --inventory — emit the deterministic JSON inventory only, ideal for diffing in CI.
  3. forensify --domains skills,credentials --include-shadows — focus on shadowed skills and credential hygiene, including backups, caches and session databases.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/alexgreensh/repo-forensics/HEAD/plugins/repo-forensics/skills/forensify/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the plugins/repo-forensics/skills/forensify folder from the GitHub repo alexgreensh/repo-forensics into my ~/.claude/skills/forensify/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/alexgreensh/repo-forensics.git && mkdir -p ~/.claude/skills && cp -r repo-forensics/plugins/repo-forensics/skills/forensify ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and move to a working directory.
  2. Clone the repo: git clone https://github.com/alexgreensh/repo-forensics.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill in: cp -r repo-forensics/plugins/repo-forensics/skills/forensify ~/.claude/skills/
  5. Verify Python 3 is available: python3 --version (no pip packages required).
  6. Restart Claude Code, then ask it to "audit my agent stack" or run forensify --inventory.
  7. Read results in ~/.cache/forensify/runs/<run>/briefing.md and briefing.json.
View source on GitHub ↗License: NOASSERTION