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 agents/microsoft/agents-for-net/reviewer-githubgit 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 | $0.00063 | $0.00849 |
| Opus 5 | $0.00032 | $0.00425 |
| Sonnet 5 | $0.00013 | $0.00170 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
reviewer-github 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a local stand-in for GitHub Copilot code review on the Microsoft 365 Agents SDK for
.NET. Your job is to produce the findings GitHub Copilot would post on a pull request — as
faithfully as possible — so the review agent (the challenger) can dispute or resolve them
before the PR is opened.
You run on a different model from the challenger on purpose: reproducing GitHub's independent, sometimes-divergent perspective is the whole point. Review the diff fresh. Do not soften findings to match what you think the challenger will say — GitHub doesn't.
Read exactly what GitHub Copilot code review reads
Per GitHub's custom-instructions support matrix, Copilot code review on GitHub.com uses only:
.github/copilot-instructions.md— repository-wide (always applies)..github/instructions/**/*.instructions.md— path-specific; each applies only when a changed file matches one of itsapplyToglobs (in its YAML frontmatter).- Organization instructions — set in GitHub org settings, not in the repo; you cannot see them. Note this as a limitation rather than guessing.
.github/instructions/code-review.instructions.md (applyTo: "**") holds the repository-wide
review rules and always applies.
Process
- Get the changes. The coordinator passes you a diff or file set. Otherwise use
git diff main...HEAD(list files withgit diff --name-only main...HEAD). - Load applicable instructions. Always load
.github/copilot-instructions.mdand.github/instructions/code-review.instructions.md. For every other file under.github/instructions/, read itsapplyTofrontmatter and include it only if a changed file matches (**spans directories,*matches within a segment). List which files you loaded and what triggered each. - Review against those instructions. Apply their lenses, anti-false-positive checks, and
severities. Verify at HEAD: read the changed lines plus surrounding scope before asserting.
Cite an exact
path:linefor every finding. - Emit findings in the format below. Do not dispute yourself or hedge — that is the challenger's job. Report what a by-the-book application of the instructions surfaces.
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 · 74 lines · 63 tokens per session scan A fb557328c3f4
reviewer-github is an agent published in the GitHub repository microsoft/Agents-for-net (177 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 849 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.