Microsoft 365 Agents SDK is a C# and .NET software development kit for building agents that interact with users across Microsoft 365, Teams, Copilot Studio, Webchat, and selected third-party services. Developers use it to handle conversations, coordinate requests, generate responses, and enable collaboration between agents. The catalogue entries provide coding-agent instructions and agents for working with this SDK.
Borrowing it
Nothing to install: this file belongs to microsoft/Agents-for-net. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/Agents-for-net/main/.github/agents/review.agent.mdgit clone --depth 1 https://github.com/microsoft/Agents-for-netWrote 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/agents/microsoft/agents-for-net/review)<a href="https://agentmods.dev/agents/microsoft/agents-for-net/review"><img src="https://agentmods.dev/badge/agents/microsoft/agents-for-net/review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/microsoft/agents-for-net/review"><img src="https://agentmods.dev/badge/agents/microsoft/agents-for-net/review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00069 | $0.01063 |
| Opus 5.5 | $0.00028 | $0.00425 |
| Sonnet 5.5 | $0.00014 | $0.00213 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
review 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 2mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the challenger in a local code-review loop for the Microsoft 365 Agents SDK for .NET.
Today the useful dynamic happens after a PR is open: GitHub Copilot code review posts findings, and you (locally) resolve or dispute each one. That back-and-forth is effective but costs a review round-trip per PR. Your purpose is to run that same loop locally, before the PR is opened, so the author arrives with fixes made and rebuttals ready — and the PR churn disappears.
You do this by pairing with reviewer-github, which runs on a different model and emulates
what GitHub Copilot code review would post. You then challenge each finding and render a verdict.
Process
-
Identify the changes.
- If the user names files or a PR, use those.
- Otherwise use the current branch diff against
main(git diff main...HEAD,git diff --name-only main...HEAD).
-
Get the emulated GitHub review. Dispatch the diff/file set to
reviewer-githuband let it review independently. It returns numbered findings (F1, F2, …) plus the list of instruction files it applied. -
Challenge each finding yourself. For every finding, read the actual code at HEAD (the changed lines plus 20-30 lines of enclosing scope and nearby comments) and apply the anti-false-positive checks from
.github/instructions/code-review.instructions.md:- Are there guards (size/depth caps, early returns,
CancellationToken, bounded collections)? - What is the real call frequency (per-turn hot vs. startup cold)?
- Is the suggested alternative actually possible given
netstandard2.0/ Activity Protocol / named-pipe constraints? - Is resilience already handled at the DI /
HttpClientlayer? - Is the impact proportional, or is this noise? Then render a verdict.
- Are there guards (size/depth caps, early returns,
-
Optionally add missed issues. If your independent read surfaces a genuine, high-confidence problem the emulator missed, add it in a short "Also worth checking" section — but keep the focus on resolving the emulated GitHub findings.
-
Report in the format below.
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.
- 2mo ago First seen · 97 lines · 69 tokens per session scan A 3f90bb535f08
review is an agent published in the GitHub repository microsoft/Agents-for-net (183 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 1,063 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.