cosmosdb-agent-kit code-review.instructions.md

cosmosdb-agent-kit code-review.instructions.md is an instructions file for GitHub Copilot from AzureCosmosDB/cosmosdb-agent-kit. It costs 860 tokens per session, scanned A, original, MIT.

A code-review checklist for the Azure Cosmos DB agent-kit repository. It defines which issues block a merge, which are recommendations, and what files and fields submissions must contain.

In plain words
What is it for?
Use it to review pull requests and check rule files, build-related changes, evaluation files, and test-scenario definitions in that repository.
Why use it?
It gives reviewers and contributors the same rules for judging changes. This reduces incomplete rule files, evaluation tasks, and test scenarios.

Instructions file for GitHub Copilot

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/azurecosmosdb/cosmosdb-agent-kit/code-review
Clone the repo
git clone --depth 1 https://github.com/AzureCosmosDB/cosmosdb-agent-kit

Made for: GitHub Copilot.

Per session 860 This file is loaded in full into every session.
When invoked 860 The same file โ€” it is already loaded in full.
Security scan A 0 findings. 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 $0.00860 $0.00860
Opus 5 $0.00430 $0.00430
Sonnet 5 $0.00172 $0.00172
Haiku 4.5 $0.00086 $0.00086

Measured 3d ago against content hash cd6bfa3816f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cosmosdb-agent-kit code-review.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured 3d 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.

.github/instructions/code-review.instructions.md ยท 75 lines

How it starts

The opening of the file, as written. The whole thing โ€” 75 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

When performing a code review, apply these checks for the cosmosdb-agent-kit repository.

The full checklist, field requirements, and per-section details live in .github/skills/code-review/checklist.md โ€” read that file for the complete rules. This file summarizes the key gates.

Severity Tiers

  • ๐Ÿ”ด Blocking: Must fix before merge.
  • ๐ŸŸก Recommendation: Should fix.
  • ๐ŸŸข Suggestion: Nice to have.

Key Gates (๐Ÿ”ด Blocking)

Rule files (skills/*/rules/*.md):

  • Frontmatter: title, impact (CRITICAL|HIGH|MEDIUM-HIGH|MEDIUM|LOW-MEDIUM|LOW), impactDescription, tags
  • Body: **Incorrect + **Correct sections with fenced code blocks
  • Filename: {prefix}-{description}.md (model-, partition-, query-, sdk-, index-, throughput-, global-, monitoring-, pattern-, tooling-, vector-)

Build:

  • AGENTS.md is generated on demand (npm run build) and is not committed; do not require it in rule PRs

Eval tasks (evals/**/*.yaml):

  • Required fields: id, name, description, tags, inputs.prompt, expected.outcomes

Test scenarios (testing-v2/scenarios/):

  • api-contract.yaml: camelCase fields, health: section required
  • tests/conftest.py: deterministic data only โ€” no uuid4(), random, faker

Scripts: Changes to compile.js/validate.js must not break existing rules.

Workflows: No hardcoded secrets. Use ${{ secrets.* }} or ${{ github.token }}.

General: No secrets, API keys, or connection strings anywhere.

Rule Provenance (๐Ÿ”ด Blocking)

Rules in this repo are created by the automated evaluation loop (LLM reviews test failures and proposes rules). Flag rules that show signs of LLM confabulation rather than verified Cosmos DB knowledge:

  • ๐Ÿ”ด Claims specific RU costs, internal limits, or SDK implementation details without a verifiable documentation link
  • ๐Ÿ”ด Attributes a test failure to a Cosmos DB "best practice" that may actually be a framework bug, test misconfiguration, or code generation error
  • ๐Ÿ”ด Invents SDK method signatures, parameters, or behaviors that don't exist in official SDK docs
  • ๐Ÿ”ด Presents a scenario-specific workaround as a universal rule (e.g., "always do X" when X only applies to the exact test that failed)
  • ๐ŸŸก Rule has no Reference link to official Microsoft documentation โ€” high hallucination risk
  • ๐ŸŸก Rule's Incorrect/Correct examples look synthetic rather than drawn from real SDK usage patterns

Read the full file on GitHub ยท 75 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. 3d ago First seen ยท 75 lines ยท 860 tokens per session scan A cd6bfa3816f8

Subscribe to this mod's changes

cosmosdb-agent-kit code-review.instructions.md is an instructions file published in the GitHub repository AzureCosmosDB/cosmosdb-agent-kit (53 stars, last pushed 10d ago), licensed MIT. It adds 860 tokens to every session, about $0.0043 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.