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 conda-env-managergit 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/conda-env-manager)<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/conda-env-manager"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/conda-env-manager/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/conda-env-manager"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/conda-env-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 System Prompt Leakage · line 50 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- high System Prompt Leakage · line 279 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00204 | $0.03074 |
| Opus 5 | $0.00102 | $0.01537 |
| Sonnet 5 | $0.00041 | $0.00615 |
| Haiku 4.5 | $0.00020 | $0.00307 |
Grade B, and why
conda-env-manager scanned grade B with 2 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 11d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
| Activate / switch env (guidance only) | Print instructions: `conda activate neuroclaw-dl` | Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
# In real implementation: subprocess.run(full_cmd, check=True) after confirmation How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conda Environment Manager (Tool Layer)
Overview
Conda is the backbone for reproducible, cross-platform environments in NeuroClaw — especially for CUDA-dependent deep learning stacks (PyTorch, TensorFlow, MONAI, nnU-Net), neuroimaging tools (ANTs, FSL wrappers, nipype), and scientific computing packages.
This skill acts as the interface-layer orchestrator for all common conda operations, preventing accidental modification of the base environment, reducing version conflicts, and enforcing best practices (isolated environments per project, environment.yml for reproducibility, explicit version pinning, dry-run previews).
Strict workflow (never skipped):
- Parse user intent from the request or context (create / export / update / remove / clone / list / activate guidance).
- Detect current conda setup (
conda info, active environment, disk space, conda version). - Propose a safe, best-practice plan:
- Prefer
--nameover--prefixfor readability - Always suggest creating a new environment instead of modifying base or existing ones
- Recommend
environment.ymlfor reproducibility and sharing - Use
--yesonly after explicit user confirmation - Warn about large downloads (CUDA stacks, large models)
- Suggest channel priority: conda-forge > pytorch/nvidia > defaults
- Prefer
- Show numbered plan + exact commands + estimated time/size + risks.
- Wait for explicit user confirmation (“YES”, “execute”, “proceed”).
- On approval: execute safely (with logging), capture output, report success/failure, and suggest next steps.
Core safety & best-practice rules
- Never modify the base environment unless explicitly requested (and double-warned)
- Prefer
conda env export --from-history > environment.ymlfor clean, reproducible specs - Use
--dry-run/ plan preview by default - Integrate with
dependency-plannerfor post-creation package installation - Log all actions to
./logs/conda_YYYYMMDD_HHMMSS.log
Quick Reference (Common NeuroClaw Tasks)
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.
- 11d ago First seen · 301 lines · 204 tokens per session scan B 8c43f6f8837f
conda-env-manager is a skill published in the GitHub repository CUHK-AIM-Group/NeuroClaw (84 stars, last pushed 5d ago), licensed MIT. It adds 204 tokens to every session and 3,074 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 2 findings (asks the agent to reveal its instructions, 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…