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 skills add hevangel/batch-review-mcp --skill batch-reviewgit clone --depth 1 https://github.com/hevangel/batch-review-mcpWrote 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/skills/hevangel/batch-review-mcp/batch-review)<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.
<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>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 | $0.00080 | $0.01937 |
| Opus 5 | $0.00040 | $0.00968 |
| Sonnet 5 | $0.00016 | $0.00387 |
| Haiku 4.5 | $0.00008 | $0.00194 |
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.
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:
-
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-browserto skip). -
List changed files:
batch-review changesOutput: a JSON array of changes:
[{"path": "main.py", "status": "M", "base_label": "Original (HEAD)", "head_label": "Modified (working tree)"}, ...]Status codes:Mmodified,Aadded,Ddeleted,Rrenamed,?untracked. -
Inspect each diff for files worth reviewing:
batch-review diff main.pyOutput:
{"path": "main.py", "diff": "--- a/...\n+++ b/...", "original": "...", "modified": "...", ...} -
Read extra context when the diff isn't enough:
batch-review file src/utils.pyOutput:
{"content": "...", "line_count": 42, "language": "python", "path": "src/utils.py"}
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.
- 9d ago First seen · 144 lines · 80 tokens per session scan A 620fa5a07c17
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…