Grim Prompter
A threat-modeling skill (`/threat-model`) for Claude Code and Codex. It inspects your codebase read-only, picks from 36 architecture workflows and 29 method prompts, and writes a threat model with file and line citations into a threat-model/ folder. You install it by cloning the repo and symlinking it into ~/.claude/skills. Repo created Oct 28, 2026.
Test results
Run with our skill harness: the skill alone in a throwaway project, invoked by name, and the real output file checked. Skills are tested in Claude Code and Cursor only so far.
| Client | Result | Last passed | What we checked |
|---|---|---|---|
| Claude Code 2.1.296 (Claude Code) | Passed Tested 2026-11-08 | 2026-11-08 | threat-model: {'threat-model/<run>/report.md written during the run': True, 'token in report': True, 'SQL injection on /notes named': True, 'unauthenticated /admin/export named': True, 'a parseable JSON report in threat- |
| Cursor 2026.11.05-86047df | Passed Tested 2026-11-08 | 2026-11-08 | threat-model: {'threat-model/<run>/report.md written during the run': True, 'token in report': True, 'SQL injection on /notes named': True, 'unauthenticated /admin/export named': True, 'a parseable JSON report in threat- |
Skill version: github.com/jmanico/grim-prompter @ 2a94457c (2026-11-08).
Earlier runs:
- Claude Code, 2026-11-04: passed
- Cursor, 2026-11-08: failed (output_check)
- Claude Code, 2026-11-08: failed (output_check)
Tested on ToolPassed badge
Maker of Grim Prompter? It passed in Claude Code, Cursor on 2026-11-08. Add this free badge to your README; it links back to this listing. Free, no strings: the badge never changes a result.
[](https://toolpassed.com/skills/grim-prompter/)Get it
The skill’s files and install instructions are in its repository: github.com/jmanico/grim-prompter.
Not working?
Fixes from our own test runs: Skill not working in Claude Code? · Skill not working in Cursor?