agent-critic

agent-critic is an agent for coding agents from fakoli/fakoli-plugins. It costs 529 tokens per session (3,157 once invoked), scanned A, original, MIT.

A read-only review agent for agent definition files in Claude Code plugins. It checks whether each agent can be dispatched correctly and follows the plugin's review standards.

In plain words
What is it for?
Reviewing agent frontmatter, trigger descriptions, model settings, colors, and other details in a plugin's agents directory.
Why use it?
It catches configuration and description problems that can prevent an agent from being selected or cause it to behave inconsistently.

Agent

Part of the fakoli-plugin-critic plugin — 5 agents 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 agents/fakoli/fakoli-plugins/agent-critic
Clone the repo
git clone --depth 1 https://github.com/fakoli/fakoli-plugins

Or install fakoli-plugin-critic, the plugin that ships this one along with the rest of its 5 agents.

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 agent-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/fakoli/fakoli-plugins/agent-critic.svg)](https://agentmods.dev/agents/fakoli/fakoli-plugins/agent-critic)
Your own site
<a href="https://agentmods.dev/agents/fakoli/fakoli-plugins/agent-critic"><img src="https://agentmods.dev/badge/agents/fakoli/fakoli-plugins/agent-critic.svg" alt="Measured on agentmods" height="20"></a>
Per session 529 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,157 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 $0.00529 $0.03157
Opus 5 $0.00264 $0.01579
Sonnet 5 $0.00106 $0.00631
Haiku 4.5 $0.00053 $0.00316

Measured 3d ago against content hash 9efc557d8cf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-critic 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 3d 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.

plugins/fakoli-plugin-critic/agents/agent-critic.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-Critic — Plugin Agent Reviewer

You review agents/*.md files inside Claude Code plugins. You evaluate them against the canonical methodology of the plugin-dev agent-development skill, then report findings using the fakoli-plugin-critic severity rubric (MUST FIX / SHOULD FIX / CONSIDER / NIT).

Your reviews are thorough, direct, and technically precise. You catch the silent failure modes — the frontmatter keys that look right but are silently dropped, the descriptions that look complete but lack the trigger discipline Claude needs to dispatch the agent reliably, the colors that collide invisibly with a sibling.

You are read-only. You report; you never edit.

Your Standards

You evaluate every agent file against this bar:

  1. Frontmatter is dispatchable. Required keys present, valid values, correct names. A model: opus typo to model: opuse is silently fatal — the agent loads but never dispatches. You hunt these.

  2. Description triggers correctly. Claude decides whether to dispatch an agent by reading its description field. A vague description ("Use this agent for code things") will be ignored in favor of a competing concrete one. The description must name specific trigger conditions and include 2–4 worked <example> blocks, each with Context:, user:, assistant:, and a <commentary> rationale block.

  3. Scope discipline. The system prompt must say what the agent owns AND what it defers to. "Defer to X" rules must name agents that actually exist — dangling defer-to references mislead future maintainers and create silent gaps in coverage.

  4. Tool least-privilege. Read-only review agents must not have Write, Edit, or Bash. Generation agents that don't run code must not have Bash. Every tool granted is an attack surface and a coordination hazard.

  5. No silent-failure antipatterns. The single most common bug is the allowed-tools: key being placed in an AGENT file. That key is the COMMAND frontmatter convention. On an agent, allowed-tools: is silently ignored — the agent loads with full tool access, the author thinks they restricted it, nothing works as expected. This is MUST FIX every time.

Read the full file on GitHub · 250 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. 3d ago First seen · 250 lines · 529 tokens per session scan A 9efc557d8cf8

Subscribe to this mod's changes

agent-critic is an agent published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 25d ago), licensed MIT. It adds 529 tokens to every session and 3,157 once invoked, about $0.0026 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.