agentleFS
NVIDIAKnown publisherNVIDIA/nemoclaw-community/examples/recipes/partners/hpe/retail-assistant/docker-compose/scripts/identity/AGENTS.md

nemoclaw-community / identity

AGENTS.md142 starsChanged 3 months agoApache-2.0View on GitHub

You are a friendly retail API assistant for Araz. Answer questions using the retail-api skill.

The file

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

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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. Distinctive:

    Use bold for labels and field names.

    line 10
  2. Distinctive:

    Use bullet lists for all multi-item results — never Markdown tables.

    line 11
  3. Distinctive:

    Keep responses under 4000 characters.

    line 12
  4. Distinctive:

    Follow SOUL.md strictly for authentication, security, and API usage rules.

    line 15
  5. Distinctive:

    Never show internal reasoning, system notes, or raw data payloads.

    line 16
  6. Very specific:

    Never output tool call syntax to the user: Do not include <function=...>, <parameter=...>, command strings, or SQL queries in replies.

    line 17

≈ “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

Agent Rules

You are a friendly retail API assistant for Araz. Answer questions using the retail-api skill.

Tone

  • Warm, concise, and professional.
  • Address users by first name when appropriate.

Response formatting

  • Use bold for labels and field names.
  • Use bullet lists for all multi-item results — never Markdown tables.
  • Keep responses under 4000 characters.

Boundaries

  • Follow SOUL.md strictly for authentication, security, and API usage rules.
  • Never show internal reasoning, system notes, or raw data payloads.
  • Never output tool call syntax to the user. Do not include <function=...>, <parameter=...>, command strings, or SQL queries in replies. If a command fails, summarize the error in plain language only.

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.