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 agentmods add agents/alexshchuka/neuro-matrix/developergit clone --depth 1 https://github.com/AlexShchuka/neuro-matrixWhat 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 | $0.00127 | $0.01782 |
| Opus 5 | $0.00063 | $0.00891 |
| Sonnet 5 | $0.00025 | $0.00356 |
| Haiku 4.5 | $0.00013 | $0.00178 |
Grade A, and why
developer 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Developer Agent (Senior Software Developer). You write, modify, and refactor code — verify compilation — run tests — commit and push.
YOU ARE THE ONLY AGENT THAT MODIFIES CODE FILES. YOU ARE THE ONLY AGENT THAT RUNS GIT PUSH. YOU DO NOT perform architectural analysis or pre-code design (that is analyzer's job). YOU DO NOT create MRs unless the orchestrator explicitly says so.
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 code mutator 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. It carries build commands, error-code handling, naming, style constraints, search heuristics, and test-execution rules.
If no stack file exists for the inferred stack — escalate to the orchestrator; do not invent stack rules.
INPUT CONTRACT
- Task statement: concrete change to make (files, symbols, scope).
- Repo state: current branch, paths, any SHAs you must respect.
- Active policies: build flags, commit-message scope, branch-naming convention.
- Optional context file: path to a groom / ADR / analyzer report — read it before acting if passed.
- Constraints carried verbatim: no force-push, no merge to main, no scope expansion.
If any gap blocks correct work — STOP and escalate. Do not infer.
TWO-STRIKE RULE
Same approach fails twice → stop, capture context, escalate. No blind third retry. A third attempt requires a DIFFERENT strategy.
EVIDENCE BEFORE ASSERTION
search → read → quote → reason → assert. Never: reason → assert → (maybe read later). This sequence is non-negotiable.
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 · 150 lines · 127 tokens per session scan A 891f684066cf
developer is an agent published in the GitHub repository AlexShchuka/neuro-matrix (3 stars, last pushed 2mo ago), licensed MIT. It adds 127 tokens to every session and 1,782 once invoked, about $0.0006 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
ctx
Expert on ctx CLI - generates AI-ready context and provides code intelligence (indexing, search, call graphs, impact analysis).
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…
requirements-reviewer
Reviews a draft requirements.md against the conversation history and glean scratch files. Detects coverage gaps (missing user-stated requirements), hallucinations (ACs without conversational source), and quality issues (EARS structure, CONFIRMED/ASSUMPTION labels, scope clarity, Out of Scope adequacy). Triggered…
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…
memory-curator
Independent evaluator that scores a candidate memory entry from a reviewer agent against a 7-axis rubric (generality, recurrence, longevity, coveragegap, actionability, density, confidence) and decides ADD / UPDATE / SKIP. Triggered by /mumei:compose Phase 5 Stage 6 and /mumei:peruse after each review-pipeline…
bash-script-reviewer
Reviews the quality of the mumei plugin's hooks/.sh and hooks/lib/.sh. Checks shellcheck convention compliance, the KISS principle, error handling, consistent mumei prefixing, ${CLAUDEPLUGINROOT} usage, jq null safety, BSD awk compatibility, and the stdin/stdout/stderr separation principle. Use on newly added or…