batch-review

batch-review is a skill for Claude Code from hevangel/batch-review-mcp. It costs 80 tokens per session (1,937 once invoked), scanned A, original, MIT.

A command-line workflow for collaborative code review. It sends anchored comments and highlights to a shared review page while also saving the review as JSON and Markdown.

In plain words
What is it for?
Use it to review diffs, pull requests, working-tree changes, or selected files with shared, line-specific feedback.
Why use it?
It keeps review feedback tied to exact lines and visible to other reviewers instead of leaving comments as disconnected prose.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the batch-review plugin — 2 skills, 1 command, 1 MCP server shipped together

Good fit Use it to review diffs, pull requests, working-tree changes, or selected files with shared, line-specific feedback.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hevangel/batch-review-mcp/batch-review
Install

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.

Any agent
npx skills add hevangel/batch-review-mcp --skill batch-review
Clone the repo
git clone --depth 1 https://github.com/hevangel/batch-review-mcp

Made for: Claude Code.

Or install batch-review, the plugin that ships this one along with the rest of its 2 skills, 1 command, 1 MCP server.

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 batch-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/hevangel/batch-review-mcp/batch-review/github.svg)](https://agentmods.dev/skills/hevangel/batch-review-mcp/batch-review)
Your own site
<a href="https://agentmods.dev/skills/hevangel/batch-review-mcp/batch-review"><img src="https://agentmods.dev/badge/skills/hevangel/batch-review-mcp/batch-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.

agentmods 80×15 button for batch-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/hevangel/batch-review-mcp/batch-review"><img src="https://agentmods.dev/badge/skills/hevangel/batch-review-mcp/batch-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,937 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 $0.00080 $0.01937
Opus 5 $0.00040 $0.00968
Sonnet 5 $0.00016 $0.00387
Haiku 4.5 $0.00008 $0.00194

Measured 9d ago against content hash 620fa5a07c17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

batch-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 9d 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.

skills/batch-review/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Batch Review CLI

A token-efficient command-line client for collaborative code review. Each verb is one process invocation that emits a single JSON document to stdout. The CLI talks to a running Batch Review server over REST; every comment and highlight also appears in the human reviewer's browser UI in real time.

When to use

Use this skill for any code review task: reviewing a git diff, a pull request, working-tree changes, or doing a structured walkthrough of changed files. Prefer it over reading files and writing prose comments manually, because the comments are anchored to line ranges, persisted to JSON + Markdown, and shared live with human reviewers.

Prerequisites

The batch-review command must be available. Install it:

pip install batch-review-mcp
# or
uv tool install batch-review-mcp

Verify: batch-review changes --help should print usage.

Output contract

Every verb prints one JSON document to stdout and exits 0 on success. On error, it prints {"error": "...", "hint": "..."} and exits non-zero. Parse stdout as JSON; ignore stderr (progress messages only).

Default workflow

Follow these steps for a typical review session:

  1. Start the server (only once per session):

    batch-review start --root .
    

    Output: {"web_url": "http://127.0.0.1:9000", "pid": 12345, "port": 9000} The browser opens automatically to the review UI (use --no-browser to skip).

  2. List changed files:

    batch-review changes
    

    Output: a JSON array of changes: [{"path": "main.py", "status": "M", "base_label": "Original (HEAD)", "head_label": "Modified (working tree)"}, ...] Status codes: M modified, A added, D deleted, R renamed, ? untracked.

  3. Inspect each diff for files worth reviewing:

    batch-review diff main.py
    

    Output: {"path": "main.py", "diff": "--- a/...\n+++ b/...", "original": "...", "modified": "...", ...}

  4. Read extra context when the diff isn't enough:

    batch-review file src/utils.py
    

    Output: {"content": "...", "line_count": 42, "language": "python", "path": "src/utils.py"}

Read the full file on GitHub · 144 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.

  1. 9d ago First seen · 144 lines · 80 tokens per session scan A 620fa5a07c17

Subscribe to this mod's changes

batch-review is a skill published in the GitHub repository hevangel/batch-review-mcp (2 stars, last pushed 3d ago), licensed MIT. It adds 80 tokens to every session and 1,937 once invoked, about $0.0004 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 2026-08-31.