agentleFS
DINAKAR-SDINAKAR-S/company-ai-os/AGENTS.md

company-ai-os

AGENTS.md2 starsChanged 3 months agoMITView on GitHub

Entry point for any AI coding agent (Cursor, Windsurf, Codex, Aider, …). The full operating manual for this vault is CLAUDE.md — read it first and follow it exactly. Everything below supplements it. This OS is designed to be run by a team: one orchestrator (you, in the main session) plus department sub-agents in .claude/agents/: 1. Dispatch resolves first. Before delegating, run DISPATCH step 1–2 (resolve the entity via entities/Routing.md, locate its path:). Hand the sub-agent the entity note +…

  • 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 33,315 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 repository7 other files it gives its agents.

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Dispatch resolves first: Before delegating, run DISPATCH step 1–2 (resolve the entity via entities/Routing.md, locate its path:).

    line 21
  2. Distinctive:

    Guardrails are inherited: Every sub-agent obeys CLAUDE.md §5 — confirmed writes, no guessed paths, no sensitive values in the vault, no …

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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

Entry point for any AI coding agent (Cursor, Windsurf, Codex, Aider, …). The full operating manual for this vault is CLAUDE.md — read it first and follow it exactly. Everything below supplements it.

The agent team

This OS is designed to be run by a team: one orchestrator (you, in the main session) plus department sub-agents in .claude/agents/:

AgentDepartmentUse for
hr-payroll[[HR]]payroll checklists, policy lookups, onboarding
marketing-strategist[[Marketing]]campaigns, content calendars, channel analysis
creative-director[[Marketing]]brand voice, creative review, direction briefs
finance-analyst[[Finance]]budgets, invoices, reports

Orchestration rules

  1. Dispatch resolves first. Before delegating, run DISPATCH step 1–2 (resolve the entity via entities/Routing.md, locate its path:). Hand the sub-agent the entity note + path in its prompt.
  2. Independent work runs in parallel. Multiple departments touched → spawn their agents concurrently, then consolidate.
  3. One logger. Sub-agents report back; the orchestrator writes the log.md lines and entity-note updates. No double-logging.
  4. Guardrails are inherited. Every sub-agent obeys CLAUDE.md §5 — confirmed writes, no guessed paths, no sensitive values in the vault, no unverified prices.

Growing the team

Copy any agent file in .claude/agents/, rename, rescope to the new department's entity note, and add it to the table above + index.md. Good next agents: support-lead, sales-ops, legal-reviewer, it-admin, data-analyst.

For agents without skill/sub-agent support

Everything works with plain prompts too — the skills in .claude/skills/ are just documented procedures. Open the relevant SKILL.md and follow its steps manually (e.g. "do what .claude/skills/session-handoff/SKILL.md says").

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.