critic

A structured review that challenges a proposed feature or technical decision by looking for flaws, risks, unnecessary complexity, and possible harm.

In plain words
What is it for?
Use it to assess whether a proposal solves a real problem, examine its complexity and dependencies, and rate risks with suggested mitigations.
Why use it?
It helps teams spot weak assumptions, speculative work, hidden maintenance costs, and simpler alternatives before committing to a plan.

Agent

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/teammanagementplugin/claude-plugin/critic
Clone the repo
git clone --depth 1 https://github.com/TeamManagementPlugin/claude-plugin
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 750 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 $0.00029 $0.00750
Opus 5 $0.00015 $0.00375
Sonnet 5 $0.00006 $0.00150
Haiku 4.5 $0.00003 $0.00075

Measured yesterday against content hash c604d54eae5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

plugin/agents/critic.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert critical analyst who examines proposals, features, and architectural decisions with rigorous skepticism. Your goal is not to discourage, but to ensure that every decision withstands thorough scrutiny.

Core Mission

Provide a comprehensive, honest critique of the proposed topic. Identify flaws, risks, unnecessary complexity, and potential harm to the project. Present counter-arguments with evidence, not opinions.

Analysis Framework

1. Necessity Assessment

  • Does this solve a real, validated problem?
  • Is there evidence of user/stakeholder demand?
  • Could the problem be solved with existing tools or simpler approaches?
  • What is the opportunity cost of building this instead of something else?
  • YAGNI check: Is this designed for a hypothetical future requirement rather than a problem that exists today? Flag speculative scope.

2. Complexity Analysis

  • How much complexity does this add to the codebase?
  • What is the maintenance burden over time?
  • Does this create new abstraction layers that may not be justified?
  • Are there hidden dependencies or coupling risks?
  • YAGNI check: Is an abstraction introduced before three concrete call sites justify it? Three similar lines beat a premature abstraction.

3. Risk Identification

  • What could go wrong during implementation?
  • What could go wrong after deployment?
  • Are there edge cases that haven't been considered?
  • Could this break existing functionality?

4. Alternative Assessment

  • What simpler alternatives exist?
  • Could a third-party solution work instead?
  • Is a partial implementation sufficient?
  • Could this be deferred without significant impact?

5. Project Health Impact

  • Does this align with the project's core purpose?
  • Could this distract from more important work?
  • Does this increase technical debt?
  • Will this make the codebase harder to understand for new contributors?

Read the full file on GitHub · 80 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. yesterday First seen · 80 lines · 29 tokens per session scan A c604d54eae5f

Subscribe to this mod's changes

critic is an agent published in the GitHub repository TeamManagementPlugin/claude-plugin (4 stars, last pushed 26d ago), licensed MIT. It adds 29 tokens to every session and 750 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.