review-loop

review-loop is a command for coding agents from yorrick/agent-skills. It costs 23 tokens per session (260 once invoked), scanned A, original, MIT.

A command that repeatedly reviews an existing pull request (PR), which is a proposed code change awaiting review. It simplifies the code, runs code and security reviews, fixes reported problems, and repeats until checks pass and no important issues remain.

In plain words
What is it for?
Use it on an existing PR to simplify changes, run parallel code and security checks, monitor CI, and apply fixes until the review is clean.
Why use it?
It turns several review and fix cycles into one repeatable process. This helps catch implementation, security, and continuous-integration problems before the PR is finished.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the dev-loop plugin — 3 commands shipped together

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/yorrick/agent-skills/review-loop
Clone the repo
git clone --depth 1 https://github.com/yorrick/agent-skills

Or install dev-loop, the plugin that ships this one along with the rest of its 3 commands.

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/commands/yorrick/agent-skills/review-loop.svg)](https://agentmods.dev/commands/yorrick/agent-skills/review-loop)
Your own site
<a href="https://agentmods.dev/commands/yorrick/agent-skills/review-loop"><img src="https://agentmods.dev/badge/commands/yorrick/agent-skills/review-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 260 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 $0.00023 $0.00260
Opus 5 $0.00012 $0.00130
Sonnet 5 $0.00005 $0.00052
Haiku 4.5 $0.00002 $0.00026

Measured 4d ago against content hash 29e048396ef9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

dev-loop/commands/review-loop.md · 25 lines

What it actually says

Review Loop

Run the review loop on an existing PR. This skips brainstorming and implementation — it goes straight to the iterative review cycle.

Execute the dev-loop script with the --review-only flag using the Bash tool:

uv run "${CLAUDE_PLUGIN_ROOT}/scripts/dev-loop.py" $ARGUMENTS

The script will:

  1. Run /simplify and commit fixes
  2. Run /code-review:code-review + /security-review in parallel
  3. Wait for CI/CD checks to complete (if any exist)
  4. If Critical/Important issues or CI failures found: fix (including re-running smoke test validation from the plan) and loop
  5. If clean and CI passing: done

Monitor progress from another terminal:

  • Status: watch -n1 cat .dev-loop/latest/status.txt
  • Full log: tail -f .dev-loop/latest/dev-loop.log
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. 4d ago First seen · 25 lines · 23 tokens per session scan A 29e048396ef9

Subscribe to this mod's changes

review-loop is a command published in the GitHub repository yorrick/agent-skills (10 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 260 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 2026-08-31.