agentleFS
Sign inStart free
wrm3wrm3/ai_project_template/CLAUDE.md

ai_project_template

CLAUDE.md1 starsChanged 12 months agoMITView on GitHub

This file follows the agents.md standard For complete instructions, see agents.md This project now uses the industry-standard agents.md format for AI agent instructions. As of October 2025, this project adopted the agents.md standard announced by OpenAI and adopted by 20+ major companies including Cursor, Google Jules, Gemini CLI, Factory, and Roo-Code. agents.md provides unified instructions for AI coding agents across all IDEs, eliminating the need for multiple IDE-specific configuration files. Claude Code automatically loads this CLAUDE.md file. Since it now…

The file

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

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Quality: test-runner (proactive), code-reviewer, debugger, qa-engineer

    line 31
  2. Distinctive:

    All content from the original CLAUDE.md has been incorporated into agents.md with enhanced best practices from industry research.

    line 50

≈ “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

AI Project Template

This file follows the agents.md standard
For complete instructions, see agents.md

This project now uses the industry-standard agents.md format for AI agent instructions.

Quick Links

  • Full Instructions: agents.md
  • SubAgents Guide: docs/CLAUDE_SUBAGENTS_GUIDE.md - NEW! 15 specialized AI agents
  • Task List: .fstrent_spec_tasks/TASKS.md
  • Project Context: .fstrent_spec_tasks/PROJECT_CONTEXT.md
  • Project Plan: .fstrent_spec_tasks/PLAN.md

What Changed?

As of October 2025, this project adopted the agents.md standard announced by OpenAI and adopted by 20+ major companies including Cursor, Google Jules, Gemini CLI, Factory, and Roo-Code.

agents.md provides unified instructions for AI coding agents across all IDEs, eliminating the need for multiple IDE-specific configuration files.

For Claude Code Users

Claude Code automatically loads this CLAUDE.md file. Since it now references agents.md, you get the benefits of the standardized format while maintaining backward compatibility.

🤖 SubAgents System

This project includes 16 specialized SubAgents for accelerated development:

  • Development: backend-developer, frontend-developer, full-stack-developer, database-expert, oracle-apex-specialist (opus)
  • Quality: test-runner (proactive), code-reviewer, debugger, qa-engineer
  • Security/DevOps: security-auditor (opus), devops-engineer, docker-specialist
  • Documentation: technical-writer, solution-architect (opus), api-designer
  • Workflow: task-expander (proactive)

Benefits:

  • 60-80% reduction in context usage
  • 10x faster for multi-component features
  • Automatic code reviews and security audits
  • Parallel processing of complex tasks

See the SubAgents Guide for complete documentation.

For Other IDE Users

Your IDE will look for agents.md directly and use the standardized format.

Migration

All content from the original CLAUDE.md has been incorporated into agents.md with enhanced best practices from industry research. Nothing was lost - everything was improved!

Original CLAUDE.md backed up as: CLAUDE.md.backup

Standard: agents.md - August 2025
See: agents.md for complete instructions

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