branch-review

branch-review is a command for Claude Code from hamr0/liteagents. It costs 0 tokens per session (4,690 once invoked), scanned A, a copy of branch-review, Apache-2.0.

A pre-merge branch review command that reports general and security findings, then performs an adversarial verification pass without changing code.

In plain words
What is it for?
Use it before a release to review the current branch and block merges on critical or high-severity findings.
Why use it?
It identifies serious issues before merging and records lower-priority findings for later cleanup, while keeping fixes as a separate authorized step.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

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.

agentmods
npx agentmods add commands/hamr0/liteagents/branch-review
Clone the repo
git clone --depth 1 https://github.com/hamr0/liteagents

Made for: Claude Code.

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 branch-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/hamr0/liteagents/branch-review.svg)](https://agentmods.dev/commands/hamr0/liteagents/branch-review)
Your own site
<a href="https://agentmods.dev/commands/hamr0/liteagents/branch-review"><img src="https://agentmods.dev/badge/commands/hamr0/liteagents/branch-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,690 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.04690
Opus 5 $0.00000 $0.02345
Sonnet 5 $0.00000 $0.00938
Haiku 4.5 $0.00000 $0.00469

Measured today against content hash 249f7748ff9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

branch-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 today.

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.

Origin

This is a copy

100% identical to branch-review — 25 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

packages/droid/commands/branch-review.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-merge review gate. Two stages — general review then a full security audit — followed by an adversarial verify pass. It never edits code: it reports findings and hands them back. Fixing is a separate, separately authorized action.

Only Critical and High findings block the merge. Everything else is appended to the fix ledger (.factory/remember/fix-ledger.md) — a local, cumulative list, living beside MEMORY.md, that /refactor (no arguments) works through between features. Like its neighbours it is a private working artifact, usually gitignored; it persists across reviews, it is not a deliverable. The report is blockers plus the ledger count, so a review converges instead of surfacing fresh nits every run. This command never runs /refactor itself — it nudges, the way /stash nudges /remember.

Run this before /release. /release will refuse to run without a review at the current HEAD SHA.

Guardrails

  • Spawn a worker and explicitly select your tool's mid tier. State the tier on the spawn — do not omit it and rely on a default. An omitted tier inherits the parent's tier, which is not the same thing as the balanced one. Pick the judgment-capable tier that is cheaper and faster than your top reasoning tier. Not the cheapest/fastest tier: on judgment work it measurably degrades (misclassification rates several times higher). Choose by tier, not by a vendor model name copied from this file — names drift, and this command ships to several tools. Fall back to running inline if your tool has no subagent mechanism.
  • Escalate, never assume. Anything you cannot decide, cannot verify, or that this spec does not cover → stop and report it to the orchestrator (the main session). Never improvise, never widen scope, never fix a side issue you noticed along the way.
  • The worker does the work itself — no delegation. The review subagent must not spawn subagents of its own. Everything it reports has to be something it read, ran, or grepped with its own tool calls: a relayed "I executed X" from a sub-worker is hearsay, and replacing hearsay with evidence is the entire point of this command. A review that delegates its work is a review of a report. (Same rule /security carries inside stage 2.)
  • No edits — two exceptions. You have no authorization to change code, even for a finding you are certain about. Report it. The only files you may write are .factory/remember/fix-ledger.md (append bullets; never rewrite or delete) and .factory/remember/last-review.md (overwrite; the review record described at the end of this file).
  • Prove it with two checks, because neither sees what the other does. git status --porcelain, at start and again before you report, proves no tracked file changed — that is the "never edits code" guarantee, and it is the one that matters. It cannot police your own two writes: .factory/ is normally gitignored, so porcelain stays empty whether you wrote the allowed files, wrote nothing, or overwrote MEMORY.md. git status --ignored does not close it either — it collapses to !! .factory/, the directory, not the files. So also take md5sum .factory/remember/* before you start and again before you report, and show the comparison: only fix-ledger.md and last-review.md may differ.

Read the full file on GitHub · 340 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. today Changed · -3 lines scan B → A 249f7748ff9e
  2. yesterday First seen · 343 lines · 0 tokens per session scan B 39a67cf7cdba

Subscribe to this mod's changes

branch-review is a command published in the GitHub repository hamr0/liteagents (22 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,690 tokens. A static security scan graded it A with 0 findings. It is 100% identical to branch-review, differing in 25 lines, and is treated as a copy.