agentleFS
camrontaylorcamrontaylor/AI-OS-Template/team_context/AGENTS.md

AI-OS-Template / team_context

AGENTS.md0 starsChanged 45 days agoMITView on GitHub

This file holds shared team-level instructions for Team OS. It is loaded when the Team OS context snapshot includes team context. Apply these instructions after the root AGENTS.md system rules and before private user or client-specific context. - Treat the Team OS server snapshot as the source of truth for team, user, and client context. - Use team_context/team-profile.md to understand what the team does. - Use team_context/operating-rules.md for shared approval, review, and working rules. - Use team_context/shared-preferences.md for team-wide output…

The file

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

8 rules. About 0 are common, 2 are distinctive, and 6 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.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Treat the Team OS server snapshot as the source of truth for team, user, and client context.

    line 11
  2. Very specific:

    Use team_context/team-profile.md to understand what the team does.

    line 13
  3. Very specific:

    Use team_context/operating-rules.md for shared approval, review, and working rules.

    line 14
  4. Very specific:

    Use team_context/shared-preferences.md for team-wide output and workflow preferences.

    line 16
  5. Very specific:

    Use team_context/prompt-tags.md only when prompt tags are needed.

    line 18
  6. Very specific:

    Keep private user notes out of team_context/.

    line 21
  7. Distinctive:

    Keep client-only information in the selected client's context, not in shared team files.

    line 23
  8. Very specific:

    Keep skills in the root or client .claude/skills/ folders.

    line 25

≈ “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

Team Context Agent Instructions

This file holds shared team-level instructions for Team OS. It is loaded when the Team OS context snapshot includes team context.

Apply these instructions after the root AGENTS.md system rules and before private user or client-specific context.

Rules

  • Treat the Team OS server snapshot as the source of truth for team, user, and client context.
  • Use team_context/team-profile.md to understand what the team does.
  • Use team_context/operating-rules.md for shared approval, review, and working rules.
  • Use team_context/shared-preferences.md for team-wide output and workflow preferences.
  • Use team_context/prompt-tags.md only when prompt tags are needed.
  • Load available brand or client files when the task needs that extra context; do not assume details that are only listed as available.
  • Keep private user notes out of team_context/. Private preferences belong in context/USER.md or context/MEMORY.md.
  • Keep client-only information in the selected client's context, not in shared team files.
  • Keep skills in the root or client .claude/skills/ folders. Do not treat team_context/ as a separate AI-OS workspace.

Folder Roles

  • team_context/AGENTS.md - team-level instructions.
  • team_context/team-profile.md - team identity and operating context.
  • team_context/operating-rules.md - shared rules for how work is handled.
  • team_context/shared-preferences.md - shared style and workflow preferences.
  • team_context/prompt-tags.md - team prompt tags.
  • brand_context/ - shared brand context.
  • clients/{slug}/ - client-specific context.

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.