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/agents-for-net/code-reviewgit clone --depth 1 https://github.com/microsoft/Agents-for-netWhat 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 | $0.00901 | $0.00901 |
| Opus 5 | $0.00451 | $0.00451 |
| Sonnet 5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
Agents-for-net code-review.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 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code review rules (Microsoft 365 Agents SDK for .NET)
These are the repository-wide rules for GitHub Copilot code review. Because they live in
.github/instructions/, GitHub Copilot applies them automatically when reviewing pull requests,
and the local review agent (.github/agents/review.agent.md) loads the same file. This is the
single source of truth for review rules — edit this file to change what both GitHub and the
local review enforce, so the two never diverge.
Path-specific rules for particular subsystems live in the sibling *.instructions.md files
(serialization, oauth-flows, cloudadapter-pipeline, proactive-messaging, streaming-response) and
apply in addition to these when a changed file matches their applyTo globs.
What NOT to comment on
- Do not comment on style, formatting, naming, or documentation wording.
- Do not comment on "best practices" that do not prevent an actual problem.
- Do not raise a finding you cannot tie to an exact
path:linewith a concrete failure. - If uncertain, stay silent. Only report high-confidence findings.
Anti-false-positive checks (perform ALL before raising any finding)
- Check for guards before flagging complexity. Look for size limits, depth caps, early
returns,
CancellationTokenchecks, and bounded collections. If a guard exists, drop the finding. - Trace the call site, not just the method. Identify callers and frequency: per-turn (hot) vs. startup/configuration (cold). State the call frequency in the finding.
- Understand platform constraints before suggesting alternatives. Verify the suggestion is
possible given Activity Protocol constraints, the
netstandard2.0API surface, and named-pipe framing requirements. - Check DI/HTTP-layer resilience before claiming "no retry". Inspect service registration,
HttpClientconfiguration, and anyIHttpClientFactorypolicies. - Distinguish sequential from nested parallelism. Two awaited async calls in one method are not nested if the first completes before the second starts.
- Estimate proportional impact. Processing a single Activity or sorting a small handler list is not worth flagging. Include estimated cost (ms, allocations) when raising performance findings.
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 · 68 lines · 901 tokens per session scan A 95dcb4e67dcf
Agents-for-net code-review.instructions.md is an instructions file published in the GitHub repository microsoft/Agents-for-net (177 stars, last pushed 3d ago), licensed MIT. It adds 901 tokens to every session, about $0.0045 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.