microsoft/openclaw-dev is an experimental template for running an OpenClaw AI assistant as a hosted service in Azure Container Apps. It supports development, testing, and single-tenant deployments, including access through Microsoft Teams and isolated execution for risky tools. The catalogue entries provide an agent, skill, and instructions for deploying and operating it.
Borrowing it
Nothing to install: this file belongs to microsoft/openclaw-dev. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/openclaw-dev/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/microsoft/openclaw-devWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/microsoft/openclaw-dev/copilot-instructions)<a href="https://agentmods.dev/instructions/microsoft/openclaw-dev/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/openclaw-dev/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/microsoft/openclaw-dev/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/openclaw-dev/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00861 | $0.00861 |
| Opus 5.5 | $0.00344 | $0.00344 |
| Sonnet 5.5 | $0.00172 | $0.00172 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
openclaw-dev copilot-instructions.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 1mo 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.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions — openclaw-dev
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. It is an alpha, single-tenant dev/test template.
When the user asks you to deploy, configure, operate, troubleshoot, connect to
Teams, or tear down this template, follow the playbook in
skills/openclaw-dev/SKILL.md.
Use this repo's own scripts, env-var contract, region list, and error catalog
instead of guessing.
Always-on rules
- Single entrypoint: drive everything through
./devclaw <cmd>(Windows:.\devclaw.cmd <cmd>), which wrapsazd. Fall back toazd up/azd deploy/azd downdirectly only if the wrapper isn't runnable. - Configuration is via
azd env set <KEY> <VALUE>beforedevclaw up— there is no.envfile to edit. Model/version/capacity are Bicep params ininfra/main.bicep(aiModelName/aiModelVersion/aiModelCapacity), not env vars. - Region:
AZURE_LOCATIONmust be in the allowed list ininfra/main.bicep. If the chosen region lacks the model SKU, setAZURE_OPENAI_LOCATIONseparately. - Teams is opt-in: default
devclaw upis browser-only — no Bot app registration, no Azure Bot, no Teams channel. To enable:azd env set ENABLE_TEAMS truethen re-rundevclaw up, or just rundevclaw teams(it prompts to enable and re-provisions). Don't suggest creating bot app registrations by default — they fail on restricted tenants. - 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. - Model scope: today this targets Azure OpenAI models only (default
gpt-5.4-mini). Do not claim Claude or other Foundry Models work today — they are "near future" scope. - Passwordless: the model is called keyless via Managed Identity
(
disableLocalAuth: true). Never add API keys or suggest key-based auth. - Secrets: never commit secrets.
_local/,.azure/,.azure-cli/,.azd-config/, the generatedteams/package/manifest.json, andteams/openclaw-teams-app.zipare gitignored — keep it that way. - Confirm destructive actions: before
devclaw down/azd down,az ad app delete, RBAC removal, or deleting state, state exactly what will be destroyed and get explicit user confirmation. Never pass--force/--no-promptto skip a confirmation the user hasn't given. - Cost: to pause, 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.
- 1mo ago First seen · 54 lines · 861 tokens per session scan A ba381ac5fa5b
openclaw-dev copilot-instructions.md is an instructions file published in the GitHub repository microsoft/openclaw-dev (25 stars, last pushed 3mo ago), licensed MIT. It adds 861 tokens to every session, about $0.0034 per session on Opus 5.5. 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
vscode buildNext.instructions.md
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
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, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.