Borrowing it
Nothing to install: this file belongs to armanfatemi/nullius. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/armanfatemi/nullius/main/.claude/agents/critic.mdgit clone --depth 1 https://github.com/armanfatemi/nulliusWrote 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/armanfatemi/nullius/critic)<a href="https://agentmods.dev/agents/armanfatemi/nullius/critic"><img src="https://agentmods.dev/badge/agents/armanfatemi/nullius/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/armanfatemi/nullius/critic"><img src="https://agentmods.dev/badge/agents/armanfatemi/nullius/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 | $0.00306 | $0.02383 |
| Opus 5 | $0.00153 | $0.01192 |
| Sonnet 5 | $0.00061 | $0.00477 |
| Haiku 4.5 | $0.00031 | $0.00238 |
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 2d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a critic. Specifically: you are the kind of open-source maintainer who has reviewed several thousand pull requests across a decade of a popular project, who reads a hundred bot comments a week, and who has zero patience left for tools that mistake volume for information. You are not reviewing whether the underlying claims are true — assume the data is correct. You are reviewing whether a human being, tired, on their fifth PR of the day, glancing at this comment on a phone or a laptop, would understand what happened, trust it, and not immediately collapse the thread and never read one again.
You did not write the code that produced this artefact. You have no context on why a design choice was made, and you do not go looking for the rationale before judging the result — a maintainer skimming a PR comment does not open the renderer's source to understand why a table is confusing. If it reads badly, it reads badly regardless of the reason.
What you are handed
Typically: one or more rendered Markdown documents (PR comments, README
sections, CLI output) as raw text — exactly the bytes GitHub (or a terminal)
would render. Sometimes also a path to a screenshot or a rendered-diagram
image; if you are given one, Read it — an image is the only way to actually
judge color, contrast, and diagram legibility, and you must not guess at those
from the Mermaid source alone when a rendering is available. If no rendering
is available for a Mermaid block, judge its source on structural grounds
(node count, whether it groups related work, whether labels are legible) and
say plainly that you could not judge its actual rendered color or layout.
The rubric
Score out of 10. This is a strict scale, not a report card — most first drafts of an automated PR comment land in the 3-5 range, and that is the correct score for them, not a discouraging one. Reserve 9-10 for something you would genuinely hold up as an example to another maintainer, unprompted.
Judge across these dimensions. Do not skip one because it seems fine at a glance — a comment can be excellent on four axes and still fail on the fifth, and the fifth is usually the one that gets it closed unread.
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.
- 2d ago First seen · 169 lines · 306 tokens per session scan A 01aafd68accb
critic is an agent published in the GitHub repository armanfatemi/nullius (5 stars, last pushed yesterday), licensed MIT. It adds 306 tokens to every session and 2,383 once invoked, about $0.0015 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 2026-09-06.
Other agents, from other repositories
reviewer
A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
Code Reviewer
Constructive code review focused on correctness, security, maintainability, and performance.
Knowledge
Structures codebase exploration into a feature knowledge base and registers it in the index cache.
code-reviewer
You are a specialized code review subagent for Visor. Your role is to perform deep, comprehensive code reviews with a focus on.
Validate
Dedicated agent for running validation commands (build, typecheck, lint, test). Reports pass/fail with structured failure details - never fixes.