critic-controller

critic-controller is a skill for Claude Code from ihabkhaled/AI-Psychiatry. It costs 36 tokens per session (217 once invoked), scanned A, original, MIT.

A review-control procedure that keeps a critic focused on the requested result and required quality.

In plain words
What is it for?
Use it to classify review findings, fix blockers, defer optional ideas, and decide when work is complete.
Why use it?
It prevents review from turning into endless rounds, invented requirements, style debates, or uncontrolled scope growth.

Skill for Claude Code

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

Part of the ai-psychiatry plugin — 55 skills shipped together

Good fit Use it to classify review findings, fix blockers, defer optional ideas, and decide when work is complete.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ihabkhaled/ai-psychiatry/critic-controller
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.

Any agent
npx skills add ihabkhaled/AI-Psychiatry --skill critic-controller
Clone the repo
git clone --depth 1 https://github.com/ihabkhaled/AI-Psychiatry

Made for: Claude Code.

Or install ai-psychiatry, the plugin that ships this one along with the rest of its 55 skills.

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-controller

README.md
[![agentmods](https://agentmods.dev/badge/skills/ihabkhaled/ai-psychiatry/critic-controller.svg)](https://agentmods.dev/skills/ihabkhaled/ai-psychiatry/critic-controller)
Your own site
<a href="https://agentmods.dev/skills/ihabkhaled/ai-psychiatry/critic-controller"><img src="https://agentmods.dev/badge/skills/ihabkhaled/ai-psychiatry/critic-controller.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 217 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 $0.00036 $0.00217
Opus 5 $0.00018 $0.00109
Sonnet 5 $0.00007 $0.00043
Haiku 4.5 $0.00004 $0.00022

Measured 8d ago against content hash 42c36ed12bf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

critic-controller 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 8d 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.

.ai/skills/critic-controller/SKILL.md · 37 lines

What it actually says

Critic Controller

Core principle

A critic checks the requested outcome; it does not become product owner.

Procedure

  1. Give the critic objective, requirements, scope, and evidence.
  2. Limit review to correctness, security, data safety, regression, and required quality.
  3. Classify each finding as blocker, required, optional, or unrelated.
  4. Fix blockers and required findings.
  5. Record optional findings without scope expansion.
  6. Stop after the critic budget and run completion gate.

Required output

Round count, classified findings, required fixes, deferred items, and completion decision.

Limits

Two rounds by default; three only for evidenced high-risk work.

Common mistakes

Do not let elegance, theoretical optimization, or speculative architecture block delivery.

Stop condition

Stop when required findings are resolved and remaining findings are optional or unrelated.

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. 8d ago First seen · 37 lines · 36 tokens per session scan A 42c36ed12bf9

Subscribe to this mod's changes

critic-controller is a skill published in the GitHub repository ihabkhaled/AI-Psychiatry (3 stars, last pushed 23d ago), licensed MIT. It adds 36 tokens to every session and 217 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

reviewing-changes

Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.

JetBrains/thinkrail · 59 tokens

reflecting-findings

Use when a reflection package hands you another agent's review findings to verify (before they become a fix request): you are the REFLECTOR, an independent skeptic. Judge each finding against the real code and settle it with reflectfinding — kept or refuted.

JetBrains/thinkrail · 58 tokens

review

Use when a green diff needs adversarial judgment in the rsc SDD chain, between verify and ship — give a review keyed to the spec/plan/constitution in 02-DOCS/wiki/sdd/, or receive one and verify each comment before agreeing. NOT running lint/type/tests (that is verify), NOT the spec-less standalone pass (that is…

ericrisco/rsc-harness · 89 tokens

code-review

Use to judge a concrete diff, branch, or GitHub PR on its own merits with no rsc-SDD spec/plan chain to key off — the spec-less giving pass behind /code-review: only findings you can defend, one verdict, read-only unless --comment or --fix. NOT the SDD gate keyed to 02-DOCS/wiki/sdd/ that also processes incoming…

ericrisco/rsc-harness · 90 tokens

code-review

Reviews diffs by severity to produce actionable feedback.

andreaswasita/copilot-agents-dojo · 13 tokens

demand-elegance

Challenges hacky fixes on non-trivial changes.

andreaswasita/copilot-agents-dojo · 16 tokens