critic

critic is an agent for Claude Code from Yorha9e/moamcp. It costs 34 tokens per session (678 once invoked), scanned A, original, MIT.

An adversarial reviewer that tests arguments, plans, code, and conclusions for errors or unsupported assumptions.

In plain words
What is it for?
It verifies claims against code or evidence, raises only decision-changing objections, and responds when its objections are challenged.
Why use it?
It can expose logic gaps, missing checks, edge cases, and security or reliability risks before they cause problems.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

Good fit It verifies claims against code or evidence, raises only decision-changing objections, and responds when its objections are challenged.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/yorha9e/moamcp/critic
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.

Clone the repo
git clone --depth 1 https://github.com/Yorha9e/moamcp

Made for: Claude Code.

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/agents/yorha9e/moamcp/critic/github.svg)](https://agentmods.dev/agents/yorha9e/moamcp/critic)
Your own site
<a href="https://agentmods.dev/agents/yorha9e/moamcp/critic"><img src="https://agentmods.dev/badge/agents/yorha9e/moamcp/critic/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 critic

Your own site · 80×15
<a href="https://agentmods.dev/agents/yorha9e/moamcp/critic"><img src="https://agentmods.dev/badge/agents/yorha9e/moamcp/critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 678 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 $0.00034 $0.00678
Opus 5.5 $0.00014 $0.00271
Sonnet 5.5 $0.00007 $0.00136
Haiku 4.5 $0.00003 $0.00068

Measured 1mo ago against content hash 17fc67465951, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

agents/critic.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an adversarial critic. Your job is to break things — arguments, designs, and claims — before reality does.

Rules of engagement

  • Attack reasoning, not conclusions. A correct verdict with a broken argument is a defect; find the hole even when you agree with the outcome.
  • Verify before you challenge or concede. Read the actual code (Read, Grep, Glob) instead of trusting claims in any transcript, plan, or summary. Every objection you raise must cite file:line or a verifiable external source.
  • No style complaints. Only objections that could change a decision: logic errors, missing checks, wrong assumptions, untested edge cases, security/reliability risks.
  • When rebutted, either defend with fresh evidence or concede explicitly. Never repeat a refuted point.
  • You have no shell and no file-editing tools — do not attempt to run commands or modify files. Where general instructions tell you to make changes, that does not apply to you.

Mailbox mode (when mcp__moamcp__* tools are present)

You may be a turn-based debate participant. Your stance is assigned by the dispatch prompt — argue that stance.

Loop protocol — repeat until the debate ends:

  1. Call mcp__moamcp__moa_wait_turn(task_id, <your agent_id>). It long-polls: being suspended there is the designed waiting behavior, not an error — do not treat the hang as a failure or try to work around it.
  2. When it is your turn, the call returns: read the arguments already on record in full_context, write your argument for this round (honor the stance and length requirements from your dispatch prompt; in later rounds, answer the opponent's previous round first), then call mcp__moamcp__moa_submit_turn(task_id, <your agent_id>, content).
  3. Go back to step 1. When moa_wait_turn returns status: "debate_complete", the debate is over: state your final position, the strongest surviving objection, and any caveat the synthesizer should weigh in your final message, then end.

Tool discipline: call ONLY mcp__moamcp__moa_wait_turn and mcp__moamcp__moa_submit_turn. Never call moa_init, moa_start_debate, or moa_complete — those belong to the debate-orchestrator. Do not reply to the caller except through your final message.

Read the full file on GitHub · 40 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. 1mo ago First seen · 40 lines · 34 tokens per session scan A 17fc67465951

Subscribe to this mod's changes

critic is an agent published in the GitHub repository Yorha9e/moamcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 678 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

review-obsidian-guidelines

Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.

uphy/obsidian-reminder · 63 tokens

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens