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/azure-samples/snippy/copilot-instructionsgit clone --depth 1 https://github.com/Azure-Samples/snippyWhat 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 | $0.00548 | $0.00548 |
| Opus 5 | $0.00274 | $0.00274 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
snippy 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 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.
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.
What it actually says
👉 Code-generation instructions
- Always target Azure Functions Python v2 (
azure-functions >= 1.23, blueprint model). - Create the global
app = func.FunctionApp()once and callapp.register_blueprint(bp). - Durable orchestrators must be
def(sync) and useyield+context.task_all(...). - Activity functions should be
async defand return JSON-serialisable data. - Use type hints throughout and a one-line Google-style docstring summary.
- Use
logging(level INFO) instead ofprint. - Access secrets via
os.environ[...]; never commit literals. - Default to Python 3.11 features (e.g.,
matchstatements are allowed). - When calling Azure SDKs, prefer their async variants (
BlobServiceClient.from_connection_string, etc.). - Return HTTP results with
azure.functions.HttpResponseand do notawaitsync methods (req.get_json(),client.create_check_status_response()).
👉 Test-generation instructions
- Use pytest + pytest-asyncio.
- Mark async tests with
@pytest.mark.asyncio. - Patch Azure SDK calls with
unittest.mock.AsyncMock / MagicMock. - Aim for 100 % branch coverage of orchestrator fan-out/fan-in paths.
- Keep test payloads small; embed them inline rather than external files.
👉 Code-review instructions
- Verify no synchronous APIs are accidentally
awaited. - Ensure every orchestrator is registered in a blueprint and yields on tasks.
- Check for missing logging, un-handled exceptions, or secret leakage.
- Confirm environment-variable names match those used in
local.settings.json. - Flag any direct network calls inside orchestrators (should be in activities).
👉 Commit-message generation instructions
- Follow Conventional Commits (
feat:,fix:,test:,chore:…). - First line ≤ 72 chars, present-tense imperative.
- Include a short body describing why and reference issues
(fixes #123).
👉 Pull-request title/description instructions
- Title: Imperative, ≤ 60 chars (e.g., “feat: add Cosmos vector search”).
- Description:
- What & why (one paragraph).
- “### Changes” bullet list.
- “### Testing” explaining manual/automated tests.
- “### Notes” for env vars, breaking changes, or deployment steps.
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.
- 2d ago First seen · 38 lines · 548 tokens per session scan A f7d92d19b5ec
snippy copilot-instructions.md is an instructions file published in the GitHub repository Azure-Samples/snippy (114 stars, last pushed 8mo ago), licensed MIT. It adds 548 tokens to every session, about $0.0027 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
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
packmind packmind-rest-api-endpoint-design.instructions.md
Instructions for PackmindHub/packmind: Conventions for designing REST API endpoints that are predictable, self-documenting, and aligned with distinct business actions. Favors dedicated action endpoints over generic status updates, and rout... .
calva-backseat-driver changelog.instructions.md
CHANGELOG.md conventions — audience, scope, and entry format for the Backseat Driver extension changelog.
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.