What is batch-review-mcp AGENTS.md?

Repository instructions for Batch Review MCP, a server and command-line client for batch code review. They cover coding standards, documentation updates, Python environment usage, session history, and supported client modes.

Use them when changing the review server, command-line client, web interface, MCP compatibility, or session-history files.

They keep changes, documentation, scripts, and review-session records consistent with the project’s rules.

How hevangel/batch-review-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to hevangel/batch-review-mcp. 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/hevangel/batch-review-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hevangel/batch-review-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hevangel/batch-review-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/hevangel/batch-review-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hevangel/batch-review-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hevangel/batch-review-mcp/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hevangel/batch-review-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hevangel/batch-review-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 900 This file is loaded in full into every session.

When invoked 900 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00900	$0.00900
Opus 5.5	$0.00360	$0.00360
Sonnet 5.5	$0.00180	$0.00180
Haiku 4.5	$0.00090	$0.00090

Measured 2mo ago against content hash 9ecad873dc93, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

batch-review-mcp AGENTS.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 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.

AGENTS.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Batch Review MCP server

Basic Standards

When you change behavior, APIs, MCP tools, or the UI, update README.md (and this file when project rules for agents change) in the same change so documentation stays accurate.
This repo uses uv for Python package management; always run scripts with uv run python
Use 4 spaces for indentation (no tabs)
Use snake_case for function and variable names
Do not call python -c with generated code; create a Python script then run it
Always print progress messages when creating Python scripts
When creating session_history/ files, use the actual current session date in the filename (YYYY-MM-DD); do not copy a prior date from older session files.
For Cursor CLI coding agent session history, populate harness version and token usage with uv run python scripts/session_history_metadata.py ...; do not write unavailable if the repo utility can extract exact values.

CLI client mode

The batch-review command supports two interfaces:

Server mode (legacy flags): batch-review [--mcp] [--root .] [--port 9000] — starts the review server + web UI. Backward compatible with all existing MCP host configs (.mcp.json, .cursor/mcp.json, etc.).
CLI client mode (subcommand verbs): batch-review <verb> [args] — token-efficient agent client that talks to a running server over REST. Verbs: start, stop, changes, diff, add-comment, list-comments, save, load, etc. See backend/cli_client.py and skills/batch-review/SKILL.md.

The dispatch rule: if sys.argv[1] is a known CLI verb, run the client; otherwise fall through to the legacy server parser. Never name a CLI verb that collides with a legacy flag (--mcp, --root, --dev, etc.).

Claude Code plugin

The repo ships a Claude Code plugin at .claude-plugin/ (CLI-only — no MCP server entry, so agents don't load tool schemas into context). The plugin bundles the batch-review skill and a /batch-review slash command.

Read the full file on GitHub · 41 lines

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.

2mo ago Changed · -35 tokens per session 9ecad873dc93
2mo ago First seen · 41 lines · 935 tokens per session scan A 97cec23da8b7

Subscribe to this mod's changes

batch-review-mcp AGENTS.md is an instructions file published in the GitHub repository hevangel/batch-review-mcp (2 stars, last pushed 8d ago), licensed MIT. It adds 900 tokens to every session, about $0.0036 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 2026-08-31.

batch-review-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
batch-review-mcp AGENTS.mdhevangel/batch-review-mcp	Instructions file	2	8d ago	MIT	A	900	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

batch-review-mcp: Instructions file for Codex