agentleFS
Sign inStart free
jmanicojmanico/grim-prompter/AGENTS.md

grim-prompter

AGENTS.md391 starsChanged 15 days agoMITView on GitHub

Grim Prompter is a threat modeling prompt library for AI coding agents. README.md is the entry point, start-here.md is the first-run guide, runbook.md is the operating contract every prompt follows, and skills/threat-model/SKILL.md is the shared Claude Code and Codex skill.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repositoryOne other file it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

4 rules. About 1 is common, 3 are distinctive, and 0 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write method instructions in original words.

    line 8
  2. Distinctive:

    Keep the project simple: plain Markdown prompts and embedded JSON contracts.

    line 9
  3. Common:

    Never publish private system material, credentials, customer data or internal planning documents.

    line 10
  4. Distinctive:

    Use a descriptive topic branch, commit reviewable changes and open a pull request against main.

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Agent Instructions

Grim Prompter is a threat modeling prompt library for AI coding agents. README.md is the entry point, start-here.md is the first-run guide, runbook.md is the operating contract every prompt follows, and skills/threat-model/SKILL.md is the shared Claude Code and Codex skill.

  • Prompts live in quick/, deep/, methods/, helpers/ and reference/. catalog.md lists every prompt.
  • Prompts are written for coding agents working under runbook.md: read-only project inspection, evidence cited by path:start-end, artifacts written to the run folder, and stage hand-offs through files. Don't reintroduce chat-window or copy-and-paste instructions.
  • Each prompt's frontmatter id is its path without .md. Keep ids, links and catalog.md in step when adding, moving or removing a prompt.
  • Write method instructions in original words. Do not copy text, tables or figures from method sources.
  • Keep the project simple: plain Markdown prompts and embedded JSON contracts. Do not introduce an application, framework or test harness.
  • Never publish private system material, credentials, customer data or internal planning documents. Never fabricate system facts or execution results.
  • Validate changes with git diff --check and check that every local link and referenced file exists. There is no application build or test suite.
  • Use a descriptive topic branch, commit reviewable changes and open a pull request against main. Merge only when the user has authorized it and all configured required checks pass. Never bypass repository protection.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free