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.
npx skills add ihabkhaled/AI-Psychiatry --skill critic-controllergit clone --depth 1 https://github.com/ihabkhaled/AI-PsychiatryWrote 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.
[](https://agentmods.dev/skills/ihabkhaled/ai-psychiatry/critic-controller)<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>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.
| Model | Per session | Once 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 |
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.
What it actually says
Critic Controller
Core principle
A critic checks the requested outcome; it does not become product owner.
Procedure
- Give the critic objective, requirements, scope, and evidence.
- Limit review to correctness, security, data safety, regression, and required quality.
- Classify each finding as blocker, required, optional, or unrelated.
- Fix blockers and required findings.
- Record optional findings without scope expansion.
- 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.
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.
- 8d ago First seen · 37 lines · 36 tokens per session scan A 42c36ed12bf9
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.
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.
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.
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…
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…
code-review
Reviews diffs by severity to produce actionable feedback.
demand-elegance
Challenges hacky fixes on non-trivial changes.