ForkFree

Agent skills and plugins

grim-prompter

by jmanico

Grim Prompter is a set of prompts and a skill that makes an AI coding agent, such as Claude Code or Codex, review your repository and write a threat model. Each finding is traced to files and lines in your code so you can check it.

Hidden gemIt gives a coding agent a structured, read-only, evidence-cited threat-modelling workflow (quick and six-stage deep runs, 36 architectures, 29 methods). It saves small teams real time on a job they would otherwise skip or pay for, and the README is clear about install, scope limits and treating repo text as untrusted. Best for indie builders and small teams wanting a first-pass threat model from their agent.
New and promisingUnder two months old. Expect rough edges and fast changes.

View on GitHub

Stars
275 +93 a day, est.
Licence
MIT
Runs on
Your computer
Setup
Easy
Language
Not stated
Age
2 days

What you can do with it

  • Run a quick threat model of your project for a chosen architecture, such as web, API or mobile
  • Run a full six-stage analysis that produces a report with mitigations and test plans
  • Review how a branch changes an existing threat model using a saved baseline

Make money with it

A freelance developer could offer low-cost security review reports for clients' apps, using this to draft the work and checking the findings by hand.

An idea, not financial advice. Check the licence before charging for anything built on it.

Ways a business could use it

  • Produce a first-pass threat model of your product before a customer security questionnaire or audit, saving consultant time
  • Re-check each major feature branch for new security risks as part of your normal release process

Can you use it commercially?

Free to use, change and sell, including in paid products. Keep the copyright notice.

Not legal advice. Read the project's licence file before building a product on it.

Getting it running

Clone the repository with git, then link the threat-model skill into Claude Code or Codex with a couple of shell commands (macOS or Linux), or add a snippet to AGENTS.md for other agents.

Follow the official instructions in the project README.

Things to check

  • Needs an existing AI coding agent, which usually means a paid subscription or API key
  • Output is a draft produced by an AI and does not certify that a system is secure
  • Reports may contain sensitive details and should be kept out of version control until reviewed
  • Install commands are written for macOS or Linux shells

Checked 31 Oct 2026. Summary drafted by AI from the project's README.

More in Agent skills and plugins

security-audit-skill cloudflare
Worth a look

A skill for coding agents that runs a structured, multi-phase security audit of a codebase. It uses separate agents to find, challenge and verify vulnerabilities, then writes the results as machine-readable records and readable reports.

53.3k stars +1411 a day MIT
ub-mode unclebob
Check the licence

ub-mode is a skill file for AI coding agents that makes them follow strict software engineering habits, such as test-driven development, low complexity and no duplicated code. It works alongside separate checking tools that measure complexity, duplication and test strength.

5.5k stars +833 a day Unclear
digital-human-koubo andyhuo520
New and promising

An agent skill that turns one photo and a short brief into a finished talking-head video with an AI presenter, including script, lip-synced clips, voice clean-up, captions and editing. It is meant for people who want to produce presenter-style videos without filming anyone.

1.5k stars +289 a day, est. MIT