{"name":"grim-prompter","repo":"jmanico/grim-prompter","url":"https://midorreal.com/project/jmanico-grim-prompter","repository":"https://github.com/jmanico/grim-prompter","description":"Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.","facts":{"license":{"value":"MIT","source":"https://github.com/jmanico/grim-prompter","checked":"22 Nov 2026"},"last_release":{"value":"v1.0.0, 8 Nov 2026","source":"https://github.com/jmanico/grim-prompter/releases","checked":"22 Nov 2026"},"releases":{"value":"1","source":"https://github.com/jmanico/grim-prompter/releases","checked":"21 Nov 2026"},"contributors":{"value":"1","source":"https://github.com/jmanico/grim-prompter/graphs/contributors","checked":"21 Nov 2026"},"archived":{"value":"no","source":"https://github.com/jmanico/grim-prompter","checked":"22 Nov 2026"}},"stars":645.0,"writeup":{"what_it_is":"Grim Prompter is a set of threat modeling prompts for AI coding agents such as Claude Code and Codex. It provides 36 architecture workflows and 29 method and analysis prompts, and produces a threat model traced to the inspected code, with mitigations and verification plans.","audience":"Developers and security reviewers threat modeling software projects with AI coding agents","claims":[{"kind":"specific","claim":"Provides 36 architecture workflows and 29 method and analysis prompts","excerpt":"Grim Prompter provides 36 architecture workflows and 29 method and analysis prompts.","status":"not_checked"},{"kind":"broad","claim":"Produces a threat model with findings traced to the inspected code","excerpt":"Get a threat model traced to your code.","status":"too_broad"},{"kind":"specific","claim":"Includes privacy workflows that examine data processing and harms to people","excerpt":"Dedicated [privacy workflows](#privacy) examine data processing and harms to people","status":"not_checked"},{"kind":"specific","claim":"Deep runs follow a six-stage workflow","excerpt":"Deep runs cover scope, system modeling, threat analysis, challenge, treatment planning, and reporting.","status":"not_checked"},{"kind":"specific","claim":"Covers MCP servers and agent tools, mapping tools to backend credentials where evidence supports it","excerpt":"the review maps tools to backend credentials and effective permissions where evidence supports them","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-16"},"why_now":null,"owner_supplied":null,"score":{"verdict":"mid","hype":69,"reality":46,"gap":23,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T07:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-11-08T17:04:35+00:00","text":"Latest release v1.0.0","source":"https://github.com/jmanico/grim-prompter/releases"},{"date":"2026-10-28T12:09:26+00:00","text":"Repository created","source":"https://github.com/jmanico/grim-prompter"}],"cite":"grim-prompter is a GitHub project at https://github.com/jmanico/grim-prompter, described there as \"Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT\".","attribution":"Data from Mid or Real, https://midorreal.com/project/jmanico-grim-prompter, checked 22 November 2026. Attribution with a link is required.","still_real":null}