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/azurecosmosdb/cosmosdb-agent-kit/copilot-instructionsgit clone --depth 1 https://github.com/AzureCosmosDB/cosmosdb-agent-kitWrote 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/azurecosmosdb/cosmosdb-agent-kit/copilot-instructions)<a href="https://agentmods.dev/instructions/azurecosmosdb/cosmosdb-agent-kit/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/azurecosmosdb/cosmosdb-agent-kit/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.00587 | $0.00587 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
cosmosdb-agent-kit 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 5d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Coding Agent Instructions
This file tells Copilot how to work with the cosmosdb-agent-kit repository.
Repository Purpose
This repository contains AI coding agent skills (best practice rules) for Azure Cosmos DB, plus a testing framework that measures how well agents apply those skills when building apps.
Key Directories
skills/cosmosdb-best-practices/— The Cosmos DB best practices skill (SKILL.md+rules/;AGENTS.mdis generated on demand, not committed)testing-v2/— The testing framework (scenarios, contracts, tests, harness)scripts/— Build scripts (compile.js compiles rules into AGENTS.md)
When Assigned to an Issue
"Run Test Iteration" issues
Follow the Agent Instructions section in the issue body exactly. The key steps are:
- Read
skills/cosmosdb-best-practices/AGENTS.md(the full rules — apply them all) - Read the scenario's
SCENARIO.mdandapi-contract.yaml - Generate code that implements the contract exactly
- Create
iteration-config.yamlin the iteration folder - Open a PR
"Create New Scenario" issues
Follow the recipe in testing-v2/CREATE-SCENARIO.md exactly. Use
testing-v2/scenarios/gaming-leaderboard/ as the format reference for all files.
When Asked to Evaluate Test Results (PR comment)
Follow the recipe in testing-v2/EVALUATE.md exactly. The key steps are:
- Read the test results from the PR comment above
- Read the scenario's
api-contract.yamland the generated code - Classify each failure (contract violation, missing rule, unclear rule, SDK quirk)
- Create or update rules in
skills/cosmosdb-best-practices/rules/ - Run
npm run buildto regenerate AGENTS.md - Update
testing-v2/IMPROVEMENTS-LOG.md - Add a concise entry to
CHANGELOG.md - Commit everything to the PR branch
Build Commands
# Compile rules into AGENTS.md (run after adding/changing rules)
npm run build
# Validate rule files
npm run validate
Conventions
- Rule files:
skills/cosmosdb-best-practices/rules/<prefix>-<description>.md - Rule prefixes: model-, partition-, query-, sdk-, index-, throughput-, global-, monitoring-, pattern-
- All API field names: camelCase
- Test data: hardcoded/deterministic, never random
- Iteration folders:
testing-v2/scenarios/<scenario>/iterations/iteration-<NNN>-<language>/
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.
- 5d ago First seen · 61 lines · 587 tokens per session scan A 439d8c46fa30
cosmosdb-agent-kit copilot-instructions.md is an instructions file published in the GitHub repository AzureCosmosDB/cosmosdb-agent-kit (54 stars, last pushed 12d ago), licensed MIT. It adds 587 tokens to every session, about $0.0029 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
dbatools AGENTS.md
AGENTS.md instructions for dataplat/dbatools, covering repository agent instructions and authoritative guidance.
CheatSheetSeries CLAUDE.md
Claude Code instructions for OWASP/CheatSheetSeries, covering claude.md and for maintainers.
agent-skills-standard CLAUDE.md
Claude Code instructions for HoangNguyen0403/agent-skills-standard, covering agent protocol and self-learning protocol.
cookiecutter-mlops-package AGENTS.md
Instructions for fmind/cookiecutter-mlops-package, covering agents.md, project overview, setup & core commands, definition of done and conventions & idioms.
pocketbase-skills CLAUDE.md
Instructions for greendesertsnow/pocketbase-skills, covering pocketbase agent skills - claude code configuration, for users, for contributors, adding new rules and rule format.
sdlc-quality copilot-instructions.md
Instructions for zircote-plugins/sdlc-quality, covering copilot instructions for sdlc plugin, project overview, repository structure, key conventions and rfc 2119 terminology.