agentleFS
Sign inStart free
joris887joris887/exosuit/.claude/prompts/CLAUDE.md

exosuit / prompts

CLAUDE.md9 starsChanged 3 months agoMITView on GitHub

Reusable prompt snippets that skills embed via @.claude/prompts/<name>.md references.

The file

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

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

  • ≈0

    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:

    Keep each prompt under 50 lines — they are embedded into skill context

    line 20
  2. Distinctive:

    Use imperative voice — these are instructions, not documentation

    line 21
  3. Distinctive:

    Never duplicate logic already in rules (rules auto-load, prompts are on-demand)

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

Prompts Directory

Reusable prompt snippets that skills embed via @.claude/prompts/<name>.md references.

Purpose

  • Shared micro-components that enforce consistency across multiple skills
  • Each file is a self-contained instruction block (typically 10-40 lines)
  • Skills reference these — prompts do not reference each other

Key Prompts

  • confidence-gate.md — 5-dimension confidence scoring (>=85 to proceed)
  • quality-gate-sequence.md — lint/test/typecheck verification sequence
  • context-budget.md — context window management instructions
  • context-prime.md — session startup context loading
  • suggest-tests.md — TDD test suggestion protocol
  • wave-execution.md — parallel task execution in waves
  • grep-first-explore.md — search-before-read exploration pattern

Conventions

  • Keep each prompt under 50 lines — they are embedded into skill context
  • Use imperative voice — these are instructions, not documentation
  • Never duplicate logic already in rules (rules auto-load, prompts are on-demand)

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