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/vscode-copilotstudio/codereviewpatternsgit clone --depth 1 https://github.com/microsoft/vscode-copilotstudioWhat 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 | $0.01724 | $0.01724 |
| Opus 5 | $0.00862 | $0.00862 |
| Sonnet 5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
CodeReviewPatterns 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Patterns
Cross-cutting patterns that recur in PR review feedback for the Copilot Studio VS Code Extension. These are not auto-detected by ESLint or Roslyn analyzers — check them manually before pushing.
High-frequency review flags:
- Missing
awaiton async LSP requests (silent failures)- PII leaked in telemetry without
<pii>tag wrapping- Concurrent sync operations not guarded by state machine
- Command handlers not pushed to
context.subscriptions- Disposable resources not cleaned up on deactivation
- Hardcoded environment URLs instead of cluster lookup
- Missing error handling on Dataverse/BAP API calls
anytype usage bypassing TypeScript strict mode- C# handlers missing null checks on nullable-enabled types
TypeScript Extension Patterns
Command Registration Must Use Subscriptions
Every commands.registerCommand call must push the disposable to context.subscriptions. Leaked commands survive extension deactivation and cause ghost behavior on reload.
// BAD - disposable leaked
commands.registerCommand('microsoft-copilot-studio.x', handler);
// GOOD - tracked for cleanup
const command = commands.registerCommand('microsoft-copilot-studio.x', handler);
context.subscriptions.push(command);
Async LSP Requests Must Be Awaited
The LSP client proxy wraps all requests with telemetry. Forgetting await silently drops errors and makes the telemetry log "success" for failed operations.
// BAD - fire-and-forget on LSP request
lspClient.sendRequest('powerplatformls/syncPush', params);
// GOOD - await and handle errors
const result = await lspClient.sendRequest('powerplatformls/syncPush', params);
PII Must Use Redaction Tags
The logger redacts <pii>text</pii> in telemetry output. Any user-identifiable data (environment IDs, agent names, email addresses, URLs with tenant info) must be wrapped.
// BAD - environment URL exposed in telemetry
logger.info(`Connecting to ${environmentUrl}`);
// GOOD - PII redacted in telemetry stream
logger.info(`Connecting to <pii>${environmentUrl}</pii>`);
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 · 229 lines · 1,724 tokens per session scan A 31043864728c
CodeReviewPatterns is an instructions file published in the GitHub repository microsoft/vscode-copilotstudio (107 stars, last pushed 3d ago), licensed MIT. It adds 1,724 tokens to every session, about $0.0086 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.