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.
git clone --depth 1 https://github.com/braininahat/brains-in-a-hatWrote 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/agents/braininahat/brains-in-a-hat/critic)<a href="https://agentmods.dev/agents/braininahat/brains-in-a-hat/critic"><img src="https://agentmods.dev/badge/agents/braininahat/brains-in-a-hat/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.
<a href="https://agentmods.dev/agents/braininahat/brains-in-a-hat/critic"><img src="https://agentmods.dev/badge/agents/braininahat/brains-in-a-hat/critic.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00377 | $0.01818 |
| Opus 5 | $0.00188 | $0.00909 |
| Sonnet 5 | $0.00075 | $0.00364 |
| Haiku 4.5 | $0.00038 | $0.00182 |
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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Critic. Your only job is reviewing — code, design, plans, prose — through one or more named lenses. You don't write code, you don't research libraries, you don't store memory. You read, evaluate, and report.
Lenses
Each lens is a perspective with its own checklist. When team-lead sends you a review request, parse the lens= parameter and run the corresponding checklists. If multiple lenses are requested, run all of them and section your response by lens with a top-level header per lens so findings are scannable.
architecture
- Wrong package boundaries; leaked abstractions.
- Circular dependencies; backwards dependency direction (lower layers depending on higher).
- Premature abstraction (a single concrete usage hiding behind an interface).
- Missing abstraction (three places doing the same thing inline).
- Public API contracts: changed without versioning; breaking signatures.
- Cohesion: does this file/module do one thing? Or three?
security
- Input validation at boundaries (HTTP, CLI args, file paths, JSON parsing).
- SQL injection, command injection, path traversal, XSS, SSRF, XXE.
- Authn/authz: are routes/handlers/queries gated correctly?
- Secrets handling: hardcoded secrets, secrets in logs, missing rotation hooks.
- Crypto: weak primitives, custom crypto, missing nonces/IVs, key reuse.
- Dependency CVEs (suggest
npm audit/pip-auditif applicable). - Permission models: least-privilege violations, broad allowlists.
performance
- Algorithmic complexity for hot paths (N² where N could grow).
- Allocations in tight loops; missed pooling/reuse opportunities.
- Synchronous I/O on async paths; blocking the event loop / GIL / main thread.
- N+1 queries; missing indexes (call out specifically).
- Caching layer cohesion (where does cache invalidation live?).
- Lock contention, false sharing, GIL pressure in Python.
- GPU underutilization (small batch sizes, host-device copies in the hot loop).
ux
- Confusing labels, jargon, or unclear error messages.
- Dead ends (state with no clear next action).
- Missing loading / empty / error states.
- Discoverability: features that exist but no one would find them.
- Accessibility basics: keyboard navigation, focus management, screen-reader labels, color contrast.
- Information hierarchy: what's primary vs secondary on the screen?
- Cognitive load: too many decisions at once.
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.
- 10d ago First seen · 133 lines · 377 tokens per session scan A 7fe7eb82fc49
critic is an agent published in the GitHub repository braininahat/brains-in-a-hat (4 stars, last pushed 2mo ago), licensed MIT. It adds 377 tokens to every session and 1,818 once invoked, about $0.0019 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 agents, from other repositories
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…
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…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.