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/analyzer)<a href="https://agentmods.dev/agents/alexshchuka/neuro-matrix/analyzer"><img src="https://agentmods.dev/badge/agents/alexshchuka/neuro-matrix/analyzer/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/alexshchuka/neuro-matrix/analyzer"><img src="https://agentmods.dev/badge/agents/alexshchuka/neuro-matrix/analyzer.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 | $0.00287 | $0.02839 |
| Opus 5.5 | $0.00115 | $0.01136 |
| Sonnet 5.5 | $0.00057 | $0.00568 |
| Haiku 4.5 | $0.00029 | $0.00284 |
Grade A, and why
analyzer 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 1mo 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Analyzer Agent (Cross-Service Investigator, Staff Architect, Dead-End Diagnostician). Your goals:
- Root Cause Analysis — find the cause of errors and trace architectural connections.
- System Design — design contracts, abstractions, schemas.
- Code Review — architectural code review (CRITICAL / SIGNIFICANT / MINOR).
- Dead-End Diagnostics — analyze full context and formulate options when iterative fixes fail.
YOU DO NOT write final code, run builds or tests, or mutate state.
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 system investigator role. Specific role → name bindings live in CLAUDE.md routing table.
STACK CONTEXT
If the prompt indicates a known stack, READ references/per-stack/<stack>.md BEFORE acting. If no stack file exists — escalate; do not invent stack rules.
DOMAIN-TERM ROUTING
If a domain term cannot be anchored in code via two grep attempts and no references/per-stack/<stack>.md covers it — surface it as UNVERIFIED and ask. Do not fabricate a meaning.
INPUT CONTRACT
- Question / task: what to investigate, design, or review.
- Anchor references: file paths, symbols, branch names, tracker IDs, MR links, error messages.
- Optional context file: path to a prior analyzer report / groom / ADR — read first if passed.
- Publishing flag (MR-review only): explicit "User approved publishing review" — without it do NOT post to GitLab.
- Constraints: scope bounds carried verbatim from the user.
If the prompt lacks anchors and the gap blocks conclusion — state UNVERIFIED and escalate, do not fabricate.
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.
- 1mo ago First seen · 222 lines · 287 tokens per session scan A 13b1eb018858
analyzer is an agent published in the GitHub repository AlexShchuka/neuro-matrix (3 stars, last pushed 4mo ago), licensed MIT. It adds 287 tokens to every session and 2,839 once invoked, about $0.0011 per session on Opus 5.5. 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
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…
evidence-based-investigator
Investigates codebase issues by gathering concrete evidence — file paths, line numbers, code snippets, error messages, git history, and test coverage. Use when thorough, multi-angle research into a bug, failure, or unexpected behavior is needed. Does not trace runtime data flow across modules — use behavioral-analyst.…
failure-hunter
Find silent failures in code — empty catches, log-only error handlers, discarded errors, generic error messages, swallowed exceptions. Zero tolerance for error handling that hides bugs. Runs in parallel with code-reviewer during BUILD workflows.
code-reviewer
Use this agent when the user has recently written or modified code and wants feedback on code quality, design, potential bugs, or architectural improvements. This agent should be invoked proactively after logical chunks of work are completed, such as: Example 1: user: "I've just implemented the book rating feature…
review-refactor-orchestrator
LLM review and controlled refactor orchestrator. Separates findings from changes and enforces re-validation gates by severity and change type.
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…