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.
npx agentmods add instructions/microsoft/openclaw-dev/agents-mdgit clone --depth 1 https://github.com/microsoft/openclaw-devWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00774 | $0.00774 |
| Opus 5 | $0.00387 | $0.00387 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
openclaw-dev AGENTS.md scanned grade A with 0 findings 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — openclaw-dev
Guidance for AI coding agents (Claude Code, OpenAI Codex, Cursor, Gemini CLI, Amp, and others) working in this repository.
This repo deploys OpenClaw as a secure, hosted AI assistant on Azure Container Apps, wired to Azure OpenAI in Foundry Models over a Managed Identity (no API keys), gated by Entra ID Easy Auth, with an optional Microsoft Teams channel. Alpha, single-tenant, dev/test.
Start here
For any deploy / configure / operate / Teams / troubleshoot / teardown request,
follow the full playbook in skills/openclaw-dev/SKILL.md.
It contains the command map, env-var contract, region list, and error catalog.
Non-negotiable rules
- Single entrypoint: use
./devclaw <cmd>(Windows.\devclaw.cmd <cmd>), a thin wrapper over the Azure Developer CLI (azd). Fall back toazddirectly only if the wrapper can't run. - Configure with
azd env set <KEY> <VALUE>beforedevclaw up. There is no.envfile. Model/version/capacity live ininfra/main.bicep, not env vars. - Teams is opt-in. Default deploy is browser-only (no bot, no Teams). To
enable the Teams add-on:
azd env set ENABLE_TEAMS truethen re-rundevclaw up(or just rundevclaw teams, which prompts and re-provisions). Don't create bot app registrations by default. - Restricted subscriptions/tenants: before
devclaw up, set whichever of these apply:SERVICE_MANAGEMENT_REFERENCE=<smr-guid>(tenants that require it on new app regs),SKIP_STORAGE=true(subscriptions whose Azure Policy blocks shared-key storage — ACA file mounts need shared keys today; gateway token + sessions won't persist across replica restarts). ACR admin is already disabled; image pulls use the container app's managed identity. - Region
AZURE_LOCATIONmust be in the allowed list ininfra/main.bicep; setAZURE_OPENAI_LOCATIONseparately if that region lacks the model SKU. - Azure OpenAI only today (default
gpt-5.4-mini). Don't claim Claude / other Foundry Models work yet — they're future scope. - Passwordless: model calls use Managed Identity (
disableLocalAuth: true). Never add or suggest API keys. - Never commit secrets.
_local/,.azure/,.azure-cli/,.azd-config/, the generatedteams/package/manifest.json, andteams/openclaw-teams-app.zipare gitignored. - Confirm before destructive actions (
devclaw down/azd down,az ad app delete, RBAC removal, deleting state): state what will be deleted and get explicit confirmation. Never use--force/--no-promptto skip it. - To pause cheaply use
devclaw stop(scale to 0, $0, state kept), notdown.
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.
- yesterday First seen · 53 lines · 774 tokens per session scan A 6556b6c852dc
openclaw-dev AGENTS.md is an instructions file published in the GitHub repository microsoft/openclaw-dev (25 stars, last pushed 2mo ago), licensed MIT. It adds 774 tokens to every session, about $0.0039 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.