review-loop

review-loop is a skill for Claude Code, Codex from ntorga/agent-starter-kit. It costs 19 tokens per session (1,222 once invoked), scanned A, original, MIT.

A review workflow for checking helper-produced code in stages. It uses one reviewer for each work group and three reviewers for a completed feature branch.

In plain words
What is it for?
It helps identify changed files, dispatch the appropriate reviewer, run reviews after each work group, and perform a broader final review.
Why use it?
It ensures work is reviewed at the right scope before reaching the user and skips review when nothing changed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit It helps identify changed files, dispatch the appropriate reviewer, run reviews after each work group, and perform a broader final review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ntorga/agent-starter-kit/review-loop
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 ntorga/agent-starter-kit --skill review-loop
Clone the repo
git clone --depth 1 https://github.com/ntorga/agent-starter-kit

Made for: Claude Code, Codex.

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 review-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/review-loop/github.svg)](https://agentmods.dev/skills/ntorga/agent-starter-kit/review-loop)
Your own site
<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/review-loop"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/review-loop/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 review-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/review-loop"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/review-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,222 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 $0.00019 $0.01222
Opus 5 $0.00010 $0.00611
Sonnet 5 $0.00004 $0.00244
Haiku 4.5 $0.00002 $0.00122

Measured 2d ago against content hash 464371e72f62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-14, from the pricing page.

Security

Grade A, and why

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.

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/review-loop/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

This skill defines how the Maestro reviews sub-agent work before it reaches the user. Two modes serve different needs. Incremental reviews (per epic) use one reviewer. Full branch reviews (at feature completion) dispatch three reviewers for full coverage.

Procedure

  1. Determine mode.

    • Incremental (default) — used for per-epic reviews during plan execution.
    • Full branch — used when all epics in impl.md are marked ✓ and the review covers the entire branch's accumulated changes. Triggered by skills/plan-management/SKILL.md → Tracking Progress.
  2. Identify scope. Determine the changed files. Use the command matching the current mode:

    • Incremental — files changed since the last commit:
      git diff HEAD --name-only; git ls-files --others --exclude-standard
      
    • Full branch — files changed against the base branch:
      git diff "$(git merge-base HEAD main)" --name-only; git ls-files --others --exclude-standard
      

    If no files changed, skip the review loop.

  3. Dispatch. Dispatch the reviewer (personas/reviewer.md) (follows: skills/dispatch/SKILL.md).

    Incremental mode — single dispatch. Reviewer runs all three lenses.

    Full branch mode — three dispatches with focused <task>:

    • First: coherence focus (follows: skills/code-coherence-review/SKILL.md).
    • Second: quality focus (follows: skills/code-quality-review/SKILL.md).
    • Third: security focus (follows: skills/code-sec-review/SKILL.md).

    For plans and non-code work, use a single dispatch regardless of mode.

    The <task> for every reviewer dispatch must include:

    • What was produced (artifact type and affected scope).
    • The original <task> or acceptance criteria.
    • For code: the list of changed files.
    • The focus area (for Full branch mode).
  4. Merge findings. When all dispatched reviewers return:

    • Union all blockers, warnings, and notes across all reviewers.
    • Deduplicate identical entries — same file, same line, same issue counts once. Dedup before verify is intentional; step 5 verifies each remaining finding.
    • If verdicts conflict, the stricter verdict wins.

Read the full file on GitHub · 83 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. 2d ago First seen · 83 lines · 19 tokens per session scan A 464371e72f62

Subscribe to this mod's changes

review-loop is a skill published in the GitHub repository ntorga/agent-starter-kit (142 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 1,222 once invoked, about $0.0001 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 2026-09-13.

Related

Other skills, from other repositories