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 dependency-plannergit 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/dependency-planner)<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/dependency-planner"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/dependency-planner/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/skills/cuhk-aim-group/neuroclaw/dependency-planner"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/dependency-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00172 | $0.03400 |
| Opus 5 | $0.00086 | $0.01700 |
| Sonnet 5 | $0.00034 | $0.00680 |
| Haiku 4.5 | $0.00017 | $0.00340 |
Grade A, and why
dependency-planner scanned grade A with 1 finding 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 10d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
info["gcc"] = subprocess.check_output(["gcc", "--version"]).decode().splitlines()[0].strip() How it starts
The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Installation Planner (Tool Layer)
Overview
Many NeuroClaw skills (especially deep-learning, neuroimaging, and custom model execution skills) fail due to missing dependencies — a key pain point identified in the MedicalClaw / OpenClaw-Medical-Skills evaluation.
This skill acts as the interface-layer planner that ensures safe, reproducible, auditable, and user-approved installations across the entire NeuroClaw hierarchy (interface → subagent → base tool).
Strict workflow (never bypassed):
- Parse the exact dependency/dependencies from the user request or error message.
- Automatically detect the local environment: OS family & version, architecture, Python version, conda/pip/virtualenv status, GCC version, NVCC/CUDA version (if GPU-relevant), available disk space & RAM.
- For each required package/tool, invoke the already-existing
multi-search-engineskill (with Google search priority) to retrieve the latest official installation instructions from the authoritative source (e.g. pytorch.org, conda-forge, nvidia.com, github.com releases page, official docs). - Perform compatibility analysis against the detected local system (CUDA/driver match, Python version support, gcc/nvcc requirements, OS limitations) and highlight potential failure risks (version conflict, missing sudo, large download, Windows WSL issues, etc.).
- Construct a clear, numbered, executable step-by-step plan, routing git-based installations through
git-essentialsandgit-workflowswhen needed. - Present the full plan, estimated time/size, risks, and exact commands to the user → wait for explicit confirmation (“YES”, “execute”, “proceed”, etc.).
- On confirmation: execute the plan safely (using conda/pip wrappers, environment isolation, logging), capture output, and provide success/failure report + rollback suggestions.
Core safety principles
- Never install silently
- Prefer conda / virtual environments over global installs
- Always version-pin where possible
- Log every command and output
- Offer dry-run / plan-only mode
- Integrate tightly with NeuroClaw’s self-evolution and safety strategy
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.
- 10d ago First seen · 330 lines · 172 tokens per session scan A e7118e9554cf
dependency-planner is a skill published in the GitHub repository CUHK-AIM-Group/NeuroClaw (83 stars, last pushed 3d ago), licensed MIT. It adds 172 tokens to every session and 3,400 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…