critic

critic is a command for Claude Code from MadaraUchiha-314/the-loop. It costs 0 tokens per session (1,116 once invoked), scanned C, original, MIT.

A command that sends a work result to a separate coding system for an independent review, then reads the review back.

In plain words
What is it for?
Use it to run configured critic reviews of work items, with prompts, working folders, time limits, and output files.
Why use it?
It provides feedback from a model that did not write the code, helping reveal problems the original author may have missed.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the the-loop plugin — 2 skills, 37 commands, 2 hooks 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/madarauchiha-314/the-loop/critic
Clone the repo
git clone --depth 1 https://github.com/MadaraUchiha-314/the-loop

Made for: Claude Code.

Or install the-loop, the plugin that ships this one along with the rest of its 2 skills, 37 commands, 2 hooks.

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 critic

README.md
[![agentmods](https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/critic.svg)](https://agentmods.dev/commands/madarauchiha-314/the-loop/critic)
Your own site
<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/critic"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/critic.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 1,116 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 5.1 $0.00000 $0.01116
Opus 5 $0.00000 $0.00558
Sonnet 5 $0.00000 $0.00223
Haiku 4.5 $0.00000 $0.00112

Measured 5d ago against content hash 68f09ddf6f5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

critic scanned grade C with 1 finding 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 5d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`; rm -rf /` is a string the critic reads, not something the shell expands.
docs/cli/commands/critic.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

critic

The seam by which the harness doing the work hands it to a different harness for a critic round, and reads back what it said.

the-loop critic list [--root .] [--format table|json]
the-loop critic run <name> (--prompt TEXT | --prompt-file PATH)
                    [--root .] [--cwd DIR] [--work-item ID] [--spec-dir PATH]
                    [--timeout SECONDS] [--output-file PATH]

A review is worth more when it comes from a model that did not write the code. This command is how that happens without either harness knowing about the other.

Where critics come from

reviews.critics[] in the repository's harness config. Each entry is either:

  • a harness the-loop has an adapter for — claude, cursor — where the invocation is derived; or
  • an explicit command (argv[0]) plus args, with element-wise placeholders: {prompt}, {promptFile}, {model}, {workItem}, {specDir}, {cwd}.

env overlays the inherited environment, and outputFormat, timeoutSeconds, cwd and enabled complete the entry.

::: danger This is executable config in a committed file A critic entry becomes an argv the CLI spawns. Review one the way you would review code, and never put a secret in env — the file is committed. :::

list

Every configured critic with its executable and whether that executable is available.

Flag Default Meaning
--root . Project root.
--format table table or json.

run

Run one named critic round.

Flag Default Meaning
(positional) The reviews.critics[] entry to run, by name.
--prompt The review prompt, inline.
--prompt-file File holding the prompt. Preferred — review prompts are long.
--root . Project root.
--cwd the critic's cwd, else --root Directory to run in.
--work-item "" Work item id, e.g. issue-117 — fills {workItem}.
--spec-dir <specDir>/<work item> Fills {specDir}.
--timeout the critic's timeoutSeconds Override for this round.
--output-file Also write the JSON envelope to this path.

Read the full file on GitHub · 119 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. 5d ago First seen · 119 lines · 0 tokens per session scan C 68f09ddf6f5c

Subscribe to this mod's changes

critic is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,116 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.