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 skills add CUHK-AIM-Group/NeuroClaw --skill method-designgit clone --depth 1 https://github.com/CUHK-AIM-Group/NeuroClawWrote 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/skills/cuhk-aim-group/neuroclaw/method-design)<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/method-design"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/method-design.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 66 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00163 | $0.01315 |
| Opus 5 | $0.00081 | $0.00658 |
| Sonnet 5 | $0.00033 | $0.00263 |
| Haiku 4.5 | $0.00016 | $0.00131 |
Grade A, and why
method-design 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 4d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Method Design
Overview
This skill implements the Framework Formalization & Theoretical Derivation process for the NeuroClaw method-design phase.
It acts as the Method Architect within the multi-agent framework:
- Reads the latest IDEA.md from the workspace.
- Designs the specific neural network structure (e.g., CNN backbone, attention modules, MRI-specific layers) tailored to the neuroscience task.
- Derives all necessary formulas (loss functions, gradients, convergence proofs, etc.) using symbolic or step-by-step reasoning.
- Produces a clean, publication-ready METHOD.md with sections: Architecture Diagram (text description), Detailed Layers, Mathematical Formulation, Implementation Notes, and Pseudocode.
If any part is ambiguous, it asks the user for clarification before proceeding.
Research use only — the output is a mathematically rigorous METHOD.md ready for experiment-controller and paper-writing.
Quick Reference (Method Flow)
| Step | Description | Output File |
|---|---|---|
| 1. Read & Parse | Load and analyze IDEA.md | 01_idea_summary.md |
| 2a. Draft Alternatives (Tournament Mode) | Sketch N candidate architectures | 02a_candidates.json |
| 2b. Lit Probe (Tournament Mode) | Per-candidate literature check via academic-research-hub | 02b_lit_check.md |
| 2c. Tournament (Tournament Mode) | Pairwise LLM-judge + Bradley-Terry ranking | 02c_ranking.csv |
| 2. Architecture Design | Define network layers & modules (top-1 from tournament if used) | 02_architecture.md |
| 3. Formula Derivation | Derive equations & proofs | 03_formulas.md |
| 4. Pseudocode & Notes | Generate implementation details | 04_pseudocode.md |
| 5. Finalize | Compile and polish | METHOD.md |
Installation
# Place files in: skills/method-design/
Tournament Mode (Optional Step 2 Expansion)
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 109 lines · 163 tokens per session scan A 727ae88c0052
method-design is a skill published in the GitHub repository CUHK-AIM-Group/NeuroClaw (83 stars, last pushed yesterday), licensed MIT. It adds 163 tokens to every session and 1,315 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
llm-tuning-patterns
Evidence-based patterns for configuring LLM parameters, based on APOLLO and Godel-Prover research.
dataflow-pattern-math-reasoning-sft
Reuse a reviewed pipeline pattern for constructing benchmark-aligned math reasoning SFT records from question-and-answer datasets with verifiable final answers.
science-vibecoding
Structured AI-assisted scientific code generation. 6 safety guards, 8 principles, 11 prompt templates. Grounded in Nature (2026).
cfd-foamagent-runtime
LangGraph-mode runtime contract for scripts/foamrun.py — preserves Foam-Agent RAG and prompt behavior. For skill-mode case generation, use cfd-skills/cfd-foamagent/SKILL.md instead (fully self-sufficient, agent-driven, no foamrun.py wrapper).
realtime_protocol_guidance_prompts
Generates short, imperative guidance prompts for the next experimental step from current video frame and protocol context. Output is optimized for voice broadcast (TTS) or AR overlay — concise, actionable, command-style — to guide researchers in real time, correct deviations, or resume experiments without breaking…
autoresearch
Run automated experiment loops to optimize algorithms, parameters, or prompts. Two modes: 'grid' for systematic parameter sweeps with Optuna TPE + WilcoxonPruner, 'creative' for Karpathy-style LLM-proposed changes. Use when: optimizing algorithm parameters, tuning thresholds, prompt optimization, ablation studies, or…