agentmods.dev

claude AGENTS.md

Repository instructions for Azure-Samples/claude, a starter project that deploys Claude models through Microsoft Foundry. Microsoft Foundry is Microsoft's service for building and hosting AI applications.

In plain words
What is it for?
Working on the starter kit, choosing between its Bicep and Terraform deployment files, and using the required Claude-on-Foundry playbook.
Why use it?
It tells coding agents how to deploy, verify, change, debug, or remove the project while following its infrastructure and safety rules.

Instructions file for CodexOpenCode

36 9d ago B scan 1,140 tokens original MIT
View the source file Azure-Samples/claude
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/azure-samples/claude/agents-md
Clone the repo
git clone --depth 1 https://github.com/Azure-Samples/claude

Made for: Codex, OpenCode.

Per session 1,140 This file is loaded in full into every session.
When invoked 1,140 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01140 $0.01140
Opus 5 $0.00570 $0.00570
Sonnet 5 $0.00228 $0.00228
Haiku 4.5 $0.00114 $0.00114

Measured 2d ago against content hash 6d7dc0a2eb5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

claude AGENTS.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Confirm before destructive actions.** Always get explicit user OK before: `azd down`, `az cognitiveservices account purge`, `az role assignment delete`, deleting `.azure-cli/`, editing `~/.claude/settings.json`. Neve
AGENTS.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Claude on Foundry Starter Kit

Guidance for AI coding agents (Claude Code, OpenAI Codex, Cursor, Gemini CLI, Amp, Goose, and others) working in this repository. GitHub Copilot reads .github/copilot-instructions.md natively; this file is the universal pointer for everyone else.

This repo deploys one or more Claude models (haiku, sonnet, opus) into a Microsoft Foundry account with a single command (azd up), then wires the Anthropic SDK and the Claude Code CLI to it over Microsoft Entra ID (no API keys). Bicep and Terraform variants ship side by side.

Short link: https://aka.ms/claude/start

Start here

For any deploy, verify, modify, debug, or teardown request, follow the full playbook in skills/claude-on-foundry/SKILL.md. It contains the decision tree, env-var contract, region matrix, error catalog, and destructive-action policy.

The always-on rules below are the same ones in .github/copilot-instructions.md, restated here so non-Copilot agents have them inline.

Non-negotiable rules

  • Two IaC variants ship side by side. The user picks ONE. Never edit or run both in the same azd env.
  • Single entrypoint: azd up from inside the chosen variant folder. Two hooks fire automatically:
  • Configure via azd env set <KEY> <VALUE> from inside the chosen variant folder. There is no .env file. See the env-var contract in .github/copilot-instructions.md.
  • CLAUDE_INDUSTRY must be lowercase: technology, finance, healthcare, education, retail, manufacturing, government, media, other. Uppercase fails with AnthropicOrganizationCreationException.
  • Honor the user's region. eastus2 and swedencentral host all three families; westus2 is sonnet + opus only. Don't silently change AZURE_LOCATION.
  • Passwordless only. Microsoft Entra ID via DefaultAzureCredential / az login. Never write CLAUDE_API_KEY, subscription IDs, tenant IDs, or tokens into any tracked file. Real values live in env vars, the gitignored .env.local, or the gitignored .azure-cli/ token cache.
  • Confirm before destructive actions. Always get explicit user OK before: azd down, az cognitiveservices account purge, az role assignment delete, deleting .azure-cli/, editing ~/.claude/settings.json. Never pass --no-prompt to skip hooks.
  • Diagnose, don't guess. When a deployment fails, identify the exact error fingerprint (715-123420, InsufficientQuota, AnthropicOrganizationCreationException, 403 Forbidden, 401 PermissionDenied) and follow the matching row in the skill's DIAGNOSE table.
  • Run the existing scripts. Don't invent ad-hoc az commands when Get-ClaudeCatalog.ps1, scripts/preflight-claude.ps1, scripts/configure-claude-code.ps1, scripts/verify-claude-code.ps1, or src/check_claude_quota.py already cover the case.

Read the full file on GitHub · 41 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 41 lines · 1,140 tokens per session scan B 6d7dc0a2eb5f

Subscribe to this mod's changes

claude AGENTS.md is an instructions file published in the GitHub repository Azure-Samples/claude (36 stars, last pushed 9d ago), licensed MIT. It adds 1,140 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai-agentsanthropicazd-templatesazure-ai-foundrybicepclaude
Related

Other instructions, from other repositories

salesforce-meta-tool-identity-propagation copilot-instructions.md

Instructions for ozgurkarahan/salesforce-meta-tool-identity-propagation, covering copilot instructions, end-session workflow, copilot-specific tips and shared knowledge base (memory wiki).

ozgurkarahan/salesforce-meta-tool-identity-propagation · 622 tokens

salesforce-meta-tool-identity-propagation AGENTS.md

Instructions for ozgurkarahan/salesforce-meta-tool-identity-propagation, covering agent instructions and shared knowledge base (memory wiki).

ozgurkarahan/salesforce-meta-tool-identity-propagation · 224 tokens

salesforce-meta-tool-identity-propagation CLAUDE.md

Instructions for ozgurkarahan/salesforce-meta-tool-identity-propagation: Read AGENT.md for all project instructions, workflow rules, and references.

ozgurkarahan/salesforce-meta-tool-identity-propagation · 22 tokens

azure-search-openai-demo AGENTS.md

Instructions for Azure-Samples/azure-search-openai-demo, covering instructions for coding agents, overall code layout, adding new data, adding a new azd environment variable and adding a new setting to "developer settings" in rag app.

Azure-Samples/azure-search-openai-demo · 5,202 tokens

azure-search-openai-demo bicep.instructions.md

Infrastructure as Code with Bicep.

Azure-Samples/azure-search-openai-demo · 749 tokens

GPT-RAG copilot-instructions.md

Instructions for Azure/GPT-RAG, covering repository development and release instructions, branching strategy, default behavior, feature development workflow and branch creation.

Azure/GPT-RAG · 1,899 tokens