deepsec Agent Skills & AI Rules

GitHub

Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents

5,159 stars TypeScript TypeScript 1 file ยท ~21,085 tokens
RAW Rules
10 Discovered Rules โ€ข ~12,348 Estimated Tokens
Quick:
Loading skill content...

.deepsec - AI Agent Protocol & Instructions

.deepsec/AGENTS.md root-instruction ~231 tokens
Raw
# Agent setup

This is a deepsec scanning workspace. Each registered project has its
own setup prompt at `data/<id>/SETUP.md` โ€” open the relevant one when
asked to set a project up.

## Common tasks

- **Set up a project for scanning**: read `data/<id>/SETUP.md` and
  follow it (read `node_modules/deepsec/SKILL.md`, then fill
  `data/<id>/INFO.md` from the target codebase).
- **Add a new project**: run `deepsec init-project <root>` โ€” it
  scaffolds `data/<id>/` and prints/writes the setup prompt for the
  new project.
- **Write a custom matcher** (only after a real true-positive shows you
  a pattern worth keeping): read
  `node_modules/deepsec/dist/docs/writing-matchers.md`.

## Reference

The deepsec skill is at `node_modules/deepsec/SKILL.md` (after
`pnpm install`). The full docs ship at
`node_modules/deepsec/dist/docs/`.