code-review-loop

A repeated process for reviewing and improving the changes between two Git revisions. It gathers review findings, applies accepted fixes, runs checks, commits the changes, and reviews them again for up to three rounds.

In plain words
What is it for?
Use it to review changes from a specified base commit to the current code, apply fixes, run validation, and repeat review until the changes are clean or the iteration limit is reached.
Why use it?
It helps catch and correct problems in a change set through multiple review cycles instead of relying on a single pass.

Skill for Claude CodeCodex

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 skills/besimple-oss/broccoli/code-review-loop
Any agent
npx skills add besimple-oss/broccoli --skill code-review-loop
Clone the repo
git clone --depth 1 https://github.com/besimple-oss/broccoli

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,555 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.01555
Opus 5 $0.00020 $0.00777
Sonnet 5 $0.00008 $0.00311
Haiku 4.5 $0.00004 $0.00155

Measured 2d ago against content hash 3ac8fd631b65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review-loop 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run_review_loop.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

prompt-templates/skills/code-review-loop/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Loop (up to 3 iterations)

Input: a git base SHA (or other explicit range) to review against (for example: <sha> or HEAD~1).

Preconditions

  • Confirm you are in the intended repo: git rev-parse --show-toplevel
  • Ensure you have a base commit SHA (prefer the commit from before the change set).
    • If none was provided and you cannot choose confidently, ask the user for the correct base SHA.
  • Start from a clean working tree (recommended):
    • git status --porcelain should be empty.
    • If it’s not empty, either commit/stash first or ask the user what to do (don’t mix unrelated changes into review fixes).
  • Ensure both CLIs are available (codex and claude) because reviewer/responder must be different vendors.

Expected runtime

Typically runs 15–45 minutes, but allow at least 120 minutes.

Do not interrupt/restart the subagent if it looks stuck. The loop script owns stuck/timeout handling and will exit on its own when it completes or when --timeout is reached. Prefer watching the periodic heartbeat output (--heartbeat-seconds) instead of tailing logs.

Why Claude sometimes looked “stuck”

Claude Code print mode can be silent in --output-format text until it finishes (including during tool work). This repo defaults Claude subprocesses to --output-format stream-json --include-partial-messages so the wrapper sees measurable progress and inactivity timeouts mainly trigger on true hangs.

Loop

Run the review loop script:

resolve_skill_dir() {
  local name="$1"
  local repo_root=""
  repo_root="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"

  local candidates=(
    "$repo_root/.agents/skills/$name"
    "$repo_root/.claude/skills/$name"
    "$HOME/.agents/skills/$name"
    "$HOME/.codex/skills/$name"
    "$HOME/.claude/skills/$name"
  )

  for d in "${candidates[@]}"; do
    if [[ -d "$d" ]]; then
      echo "$d"
      return 0
    fi
  done

  echo "Error: skill '$name' not found in repo-scoped or user-scoped skill dirs." >&2
  return 1
}

CODE_REVIEW_LOOP_SKILL_DIR="$(resolve_skill_dir code-review-loop)"
python3 "$CODE_REVIEW_LOOP_SKILL_DIR/scripts/run_review_loop.py" <base-sha>

Read the full file on GitHub · 105 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 105 lines · 40 tokens per session scan A 3ac8fd631b65

Subscribe to this mod's changes

code-review-loop is a skill published in the GitHub repository besimple-oss/broccoli (285 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 1,555 once invoked, about $0.0002 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 2026-08-30.