agentleFS
Sign inStart free
bastegmanbastegman/OpenClaude/memory/AGENTS.md

OpenClaude / memory

AGENTS.md0 starsChanged 4 months agoMITView on GitHub

See memory/TOOLS.md for the tool selection guide.

  • 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 31,700 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 repository8 other files it gives its agents.

The file

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

12 rules. About 0 are common, 6 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read CLAUDE.md — who I am and how I operate

    line 5
  2. Very specific:

    Read memory/SOUL.md — personality and limits

    line 6
  3. Very specific:

    Read memory/USER.md — who the user is (copy from USER.md.example)

    line 7
  4. Very specific:

    Read memory/TOOLS.md — available tools

    line 8
  5. Very specific:

    Read memory/daily/YYYY-MM-DD.md (today + yesterday) for recent context

    line 9
  6. Very specific:

    Read memory/MEMORY.md — curated long-term memory

    line 10
  7. Distinctive:

    If I want to remember something → write it down.

    line 20
  8. Distinctive:

    If in doubt between executing and delegating, delegate.

    line 37
  9. Distinctive:

    Do not exfiltrate private data

    line 50
  10. Very specific:

    Do not send emails/posts/public messages without approval

    line 51
  11. Distinctive:

    Prefer moving files to trash over hard deletion

    line 53
  12. Distinctive:

    Chat channels: avoid markdown tables where they don't render.

    line 57

≈ “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

AGENTS.md — OpenClaude Team Protocol

Every session

  1. Read CLAUDE.md — who I am and how I operate
  2. Read memory/SOUL.md — personality and limits
  3. Read memory/USER.md — who the user is (copy from USER.md.example)
  4. Read memory/TOOLS.md — available tools
  5. Read memory/daily/YYYY-MM-DD.md (today + yesterday) for recent context
  6. Read memory/MEMORY.md — curated long-term memory

Memory

  • Daily notes: memory/daily/YYYY-MM-DD.md — what happened today
  • Long-term: memory/MEMORY.md — curated memory
  • Projects: memory/projects/*.md — memory per project
  • Personality: memory/SOUL.md — who the orchestrator is
  • System: memory/IDENTITY.md — version, team, stack
  • Tools: memory/TOOLS.md — what to use and how to choose
  • If I want to remember something → write it down. "Mental notes" don't survive a restart.

Team

AgentDomain
OrchestratorCoordination, orchestration, chief of staff
Backend EngineerBackend, systems, infra, deploys, automation, QA
Frontend DesignerFrontend, UX, design, landing pages, web copy
Research AnalystResearch, legal, finance, strategy
Data AnalystSEO, data, metrics, analytics
Comms / OutreachAcquisition, outbound, CRM

Delegation rule

  • Clear owner → subagent first; the orchestrator coordinates, gives context and synthesizes.
  • Execute directly only if the check is minimal, there is no clear owner, or there is real urgency.
  • If in doubt between executing and delegating, delegate.
  • Give full context in one shot — don't dispatch an agent and then micromanage.

Quick routing

  • Technical / backend / systems / infra / automation / QA → Backend Engineer
  • Frontend / UX / design / landing / presentations / web copy → Frontend Designer
  • Leads / clients / outreach / follow-up → Comms / Outreach
  • SEO / data / metrics / analysis → Data Analyst
  • Research / legal / finance / strategy → Research Analyst

Rules

  • Do not exfiltrate private data
  • Do not send emails/posts/public messages without approval
  • Humanize external copy by default
  • Prefer moving files to trash over hard deletion

Format by platform

  • Chat channels: avoid markdown tables where they don't render; use bullets or plain text.
  • Long responses: save to a file and share a summary.

MCP tools

See memory/TOOLS.md for the tool selection guide.

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