agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/entra-agentid-samples/CLAUDE.md

entra-agentid-samples

CLAUDE.md12 starsChanged 7 months agoMITView on GitHub

Guidance for Claude Code (and other agent tools) working in this repository. Microsoft Entra Agent ID sample agents that demonstrate the sidecar identity pattern: the Microsoft Entra SDK for Agent ID runs as a companion container and handles token acquisition (client credentials, federated identity credential, on-behalf-of) so the agent code never touches secrets. Variants: - sidecar/dev/ — local-LLM (Ollama + LangChain) - sidecar/aws/ — AWS Bedrock (Claude + Azure→AWS OIDC) - sidecar/weather-api/ — shared downstream API - deploy/azure/container-apps/ — Azure…

  • Reads credentials

The file

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

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Always confirm Azure account, tenant ID, and subscription ID with the user before any deploy / provision / cleanup command.

    line 26
  2. Very specific:

    Never commit .env, deploy-vars.sh, tenant GUIDs, app/client GUIDs, or secrets.

    line 27
  3. Distinctive:

    Prefer editing existing files over creating new ones.

    line 28

≈ “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

CLAUDE.md

Guidance for Claude Code (and other agent tools) working in this repository.

What this repository is

Microsoft Entra Agent ID sample agents that demonstrate the sidecar identity pattern: the Microsoft Entra SDK for Agent ID runs as a companion container and handles token acquisition (client credentials, federated identity credential, on-behalf-of) so the agent code never touches secrets.

Variants:

  • sidecar/dev/ — local-LLM (Ollama + LangChain)
  • sidecar/aws/ — AWS Bedrock (Claude + Azure→AWS OIDC)
  • sidecar/weather-api/ — shared downstream API
  • deploy/azure/container-apps/ — Azure Container Apps deployment tutorials
  • scripts/ — PowerShell bootstrap for Blueprint + Agent Identity + Client SPA

Skills

Skills live under .claude/skills/<name>/SKILL.md. When the user's task matches a skill's description, read that SKILL.md in full before acting:

  • entra-agent-id-setup — Blueprint + Agent Identity + Client SPA setup in Microsoft Entra ID
  • deploy-agent-aca-dev — deploy the local-LLM sample to Azure Container Apps
  • deploy-agent-aca-aws — deploy the AWS Bedrock sample to Azure Container Apps

Operational rules

  • Always confirm Azure account, tenant ID, and subscription ID with the user before any deploy / provision / cleanup command.
  • Never commit .env, deploy-vars.sh, tenant GUIDs, app/client GUIDs, or secrets.
  • Prefer editing existing files over creating new ones.
  • For pushes, PRs, merges, or force-pushes: always confirm with the user first.

Further reading

See README.md for the high-level repository tour and .github/copilot-instructions.md for the GitHub Copilot equivalent of this file.

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