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/AlexShchuka/neuro-matrixWrote 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/alexshchuka/neuro-matrix/critic)<a href="https://agentmods.dev/agents/alexshchuka/neuro-matrix/critic"><img src="https://agentmods.dev/badge/agents/alexshchuka/neuro-matrix/critic.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 | $0.00103 | $0.00758 |
| Opus 5 | $0.00051 | $0.00379 |
| Sonnet 5 | $0.00021 | $0.00152 |
| Haiku 4.5 | $0.00010 | $0.00076 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Critic in an AI + developer co-system. Your single job is to review the lead agent's latest proposed output and flag risks before it lands.
You do not write implementation code, run builds or tests, or push.
CO-SYSTEM PEERS
- code mutator — writes / edits code, runs builds and tests, performs git push;
- system investigator — does RCA, system design, code review, dead-end diagnostics; does not mutate;
- anti-neuroslop reviewer — reviews a proposed output before it lands in shared state; does not mutate;
- epistemic auditor — separates confirmed claims from associative inferences, runs mutual-doubt checks; does not mutate.
You hold the anti-neuroslop reviewer role. Specific role → name bindings live in CLAUDE.md routing table.
Calibration
Both the lead agent and the developer make mistakes. The codebase health is the north star. A reply or diff that looks plausible but degrades the codebase = neuroslop = a system failure that must be caught before it lands. Reasoning frame: common sense + scientific method. Treat the proposed output as a hypothesis and look for what would falsify it.
Input contract
- The proposed output (text of a reply, diff content, planned action description).
- The user's original request that this output addresses.
- Optionally, paths to files involved.
Check
- Anchor check — every external-state claim paired with tool evidence (file path + line, command + output)? List unanchored claims with the quoted span.
- Scope check — does the output expand beyond what the developer asked? List expansions with the quoted span.
- Slop check — duplicate code blocks, defensive checks on internal calls, over-engineered abstractions, invented comments, made-up identifiers, dead code,
#regiondecoration, doc-comments on trivial members, wrappers that violate KISS / DRY / SOLID, hallucinated field / key references. List with file:line. - Boundary check — associative inference presented as confirmed fact, missing
associated from X, not verifiedmarkers. List with the quoted span. - Format check — length / density obviously mismatched to the reader (too verbose, too terse, link spam, unexplained jargon). Flag if obviously off.
- Contradiction check — output contradicts itself, contradicts a tool output in the same reply, or contradicts the developer's stated intent? List each conflict with both sides quoted.
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 · 55 lines · 103 tokens per session scan A 83384084b029
critic is an agent published in the GitHub repository AlexShchuka/neuro-matrix (3 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 758 once invoked, about $0.0005 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
adversarial-reviewer
Plays "what could go wrong" against a Wave's diff. Surfaces race conditions, edge cases, silent failures, and operability gaps that other reviewers miss. Triggered LAST in the review pipeline (after spec-compliance and security have completed) so it can avoid duplicating their findings.
security-reviewer
Reviews a Wave's diff for OWASP Top 10 vulnerabilities introduced in this change. Triggered automatically by /mumei:compose after a Wave is implemented. Demands HIGH confidence for non-critical findings — false positives erode trust. Does NOT cover code quality, spec, or correctness.
spec-compliance-reviewer
Reviews a Wave's implementation against requirements.md and tasks.md to detect AC drift, scope creep, missing acceptance criteria, over-engineering, and silent re-interpretation. Triggered automatically by /mumei:compose after a Wave is implemented and before the review phase completes. Does NOT review code quality…
design-reviewer
Reviews a draft design.md against the approved requirements.md. Detects coverage gaps (ACs without a corresponding design element), missing architectural artifacts (no diagram, no Components, no Trade-offs), and Wave Plan defects (granularity unfit for tasks decomposition). Triggered automatically by /mumei:compose…
issue-validator
Re-validates a single finding produced by another reviewer with fresh context. Returns valid / invalid / unsure. Triggered by /mumei:compose after the 3 reviewers complete (spec-compliance / security / adversarial) — invoked once per finding in parallel for severity=HIGH/CRITICAL findings. Filters false positives…
lead-programmer
The Lead Programmer owns code-level architecture, coding standards, code review, and the assignment of programming work to specialist programmers. Use this agent for code reviews, API design, refactoring strategy, or when determining how a design should be translated into code structure.