agentrc: Command for GitHub Copilot

.github/prompts/review.prompt.md

review is a command for GitHub Copilot from microsoft/agentrc. It costs 25 tokens per session (131 once invoked), scanned A, original, MIT.

A multi-reviewer code-review command that asks three separate AI reviewers to inspect a change, compare their findings, and produce one ordered fix list. Code review is the process of checking proposed code for defects and risks.

In plain words
What is it for?
Use it to review a branch or pull request and receive prioritized findings with files, lines, and suggested changes.
Why use it?
It reduces duplicated or unreliable findings by comparing reviews and removing issues judged to be false positives.

Command for GitHub Copilot ✓ vendor

Written for GitHub Copilot: a Copilot chat mode or prompt. Also seen: mentions subagents; mentions Codex.

This is microsoft/agentrc's own configuration. It tells GitHub Copilot how to work on agentrc itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentrc configures →

About the project

AgentRC prepares repositories for AI coding agents by analyzing their code and generating project-specific instructions, evaluations, and development configuration. It is used through a CLI, VS Code extension, or CI pipeline to measure AI readiness, keep context useful, and detect drift; the catalogue entries support these repository-preparation workflows.

microsoft/agentrc · 1,052 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to microsoft/agentrc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/microsoft/agentrc/main/.github/prompts/review.prompt.md
Clone the repo
git clone --depth 1 https://github.com/microsoft/agentrc

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/commands/microsoft/agentrc/review.svg)](https://agentmods.dev/commands/microsoft/agentrc/review)
Your own site
<a href="https://agentmods.dev/commands/microsoft/agentrc/review"><img src="https://agentmods.dev/badge/commands/microsoft/agentrc/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 131 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00025 $0.00131
Opus 5 $0.00013 $0.00066
Sonnet 5 $0.00005 $0.00026
Haiku 4.5 $0.00003 $0.00013

Measured yesterday against content hash ef189ec8ae13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 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.

.github/prompts/review.prompt.md · 12 lines

What it actually says

Run a multi-model code review:

  1. Invoke code-review-opus, code-review-gemini, and code-review-codex as three parallel subagents
  2. Cross-grade: have each reviewer evaluate the other two reviews for false positives and missed issues
  3. Synthesize a deduplicated list of findings ordered by severity (Critical > Major > Minor > Nit)
  4. Output one final fix list with file, line, and suggested change for each item
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. yesterday First seen · 12 lines · 25 tokens per session scan A ef189ec8ae13

Subscribe to this mod's changes

review is a command published in the GitHub repository microsoft/agentrc (1,052 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 131 once invoked, about $0.0001 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 2026-09-06.