Cosmos3 Env Troubleshoot
NVIDIA/cosmos-framework
Diagnose and fix Cosmos3 environment, installation, and runtime errors.
Use this quip-miner sub-skill for CPU, CUDA, Metal, Modal, and QPU mining commands, backend dependencies, QPU budgets, unified streaming, and PoW/mempool scheduling.
Install Mining Backends
$ npx skills add VectorSpaceLab/AREX-Skill --skill mining-backends -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill mining-backends --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends .claude/skills/mining-backends && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mining-backends" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends into .claude/skills/mining-backends/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mining-backends", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backendsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add VectorSpaceLab/AREX-Skill --skill mining-backends -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill mining-backends --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends .agents/skills/mining-backends && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mining-backends" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends into .agents/skills/mining-backends/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mining-backends", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill mining-backends -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill mining-backends --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends .cursor/skills/mining-backends && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mining-backends" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends into .cursor/skills/mining-backends/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mining-backends", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add VectorSpaceLab/AREX-Skill --skill mining-backends -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill mining-backends --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends .gemini/skills/mining-backends && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mining-backends" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends into .gemini/skills/mining-backends/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mining-backends", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install VectorSpaceLab/AREX-Skill mining-backendsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add VectorSpaceLab/AREX-Skill --skill mining-backends -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends .github/skills/mining-backends && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mining-backends" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends into .github/skills/mining-backends/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mining-backends", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add VectorSpaceLab/AREX-Skill --skill mining-backends -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill mining-backends --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends .opencode/skills/mining-backends && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mining-backends" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends into .opencode/skills/mining-backends/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mining-backends", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
mining-backends- GitHub stars
- 328
- Token cost
- ~753 tokens
- SKILL.md length
- 257 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 159
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Use this quip-miner sub-skill for CPU, CUDA, Metal, Modal, and QPU mining commands, backend dependencies, QPU budgets, unified streaming, and PoW/mempool scheduling.
- DevOps & Cloud work in your project
- SKILL.md covers Route By Task, Common Commands, Key Rules and Boundaries
- Runs Python scripts from its folder
What it does
Mining Backends is an agent skill from VectorSpaceLab/AREX-Skill. Use this quip-miner sub-skill for CPU, CUDA, Metal, Modal, and QPU mining commands, backend dependencies, QPU budgets, unified streaming, and PoW/mempool scheduling.
Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/backend-workflows.md`, `references/troubleshooting.md` and `references/unified-streaming-and-mempool.md`).
It sits in DevOps & Cloud. It works with CUDA. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is AGPL-3.0.
When your agent uses it
- DevOps & Cloud work in your project
Example prompts
- “/mining-backends”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Mining Backends loads about 753 tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 45 tokens; SKILL.md has 257 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its AGPL-3.0 licence (© VectorSpaceLab). 257 words, ~753 tokens.
Download SKILL.mdSave it as
.claude/skills/mining-backends/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- mining-backends
- description
- Use this quip-miner sub-skill for CPU, CUDA, Metal, Modal, and QPU mining commands, backend dependencies, QPU budgets, unified streaming, and PoW/mempool scheduling.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- AGPL 3.0
Mining Backends
Use this sub-skill when the user needs to run, tune, or troubleshoot quip-miner CPU/GPU/QPU mining backends or understand PoW plus mempool scheduling on those workers.
Route By Task
- Backend commands and tuning: Read
references/backend-workflows.mdfor CPU SA, CUDA, Metal, Modal, D-Wave QPU, gate-model QPU, optional dependencies, and safe command patterns. - Streaming and mempool architecture: Read
references/unified-streaming-and-mempool.mdfor the stream-driver subprocess, shared-memory ring, feeder specs, PoW/mempool preemption, and no-inline-sampling invariant. - Backend failures: Read
references/troubleshooting.mdfor CUDA allocation, Metal host mismatch, Modal unavailable, QPU credential/budget, topology binding, and mempool-owner problems. - Availability probe: Run
scripts/backend_probe.py --jsonor the rootscripts/quip_backend_probe.py --jsonbefore claiming backend availability.
Common Commands
quip-miner cpu --validator ws://127.0.0.1:9944 --num-cpus 4 --signer-key ~/.quip-miner/signing.json
quip-miner gpu --validator ws://127.0.0.1:9944 --gpu-backend local --signer-key ~/.quip-miner/signing.json
quip-miner gpu --validator ws://127.0.0.1:9944 --gpu-backend metal --signer-key ~/.quip-miner/signing.json
quip-miner gpu --validator ws://127.0.0.1:9944 --gpu-backend modal --signer-key ~/.quip-miner/signing.json
quip-miner qpu --validator ws://127.0.0.1:9944 --qpu-type dwave --daily-budget 30s --signer-key ~/.quip-miner/signing.jsonPrefer config-driven production runs (quip-miner --config config.toml) once the backend inventory is known.
Key Rules
- Every worker mines PoW continuously. Mempool jobs preempt PoW on the same workers when the group owns mempool; PoW resumes afterward.
- CPU/GPU mempool defaults on; QPU mempool defaults off and must be explicitly opted into in the vendor section.
- A live miner pulls topology from the chain. Passing
--topologyto live mining commands is an error. - CUDA guidance requires actual CUDA runtime evidence; a CPU import is not enough.
- Metal has no CPU fallback. On non-Apple hosts, provide config/docs guidance only.
- Do not run paid QPU sampling or Modal cloud jobs unless the operator explicitly accepts credentials, network, cost, and runtime.
Boundaries
- Route TOML schema and supervisor deployment to
../config-supervisor-deployment/SKILL.md. - Route wallet, bootstrap, descriptor, and solver registration to
../identity-wallet-bootstrap/SKILL.md. - Route telemetry and attempts archives to
../telemetry-attempt-archive/SKILL.md. - Route topology/proof replay and D-Wave h/J range details to
../topology-proof-validation/SKILL.md.
© VectorSpaceLab, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts, references) in skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/backend-workflows.md
- references/troubleshooting.md
- references/unified-streaming-and-mempool.md
- scripts/backend_probe.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Mining Backends next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Mining Backends this skillVectorSpaceLab/AREX-Skill | 328 | — | ~753 | Automated safety check: Pass | AGPL-3.0 | |
| Cosmos3 Env TroubleshootNVIDIA/cosmos-framework | 556 | — | ~1.3k | Automated safety check: Notes | Custom licence | |
| Install Miles Diffusionradixark/miles_diffusion | 107 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Init GPU Serverdrawthingsai/draw-things-community | 579 | — | ~2.2k | Automated safety check: Pass | GPL-3.0 | |
| Cosmos3 SetupNVIDIA/cosmos-framework | 556 | — | ~1.1k | Automated safety check: Notes | Custom licence | |
| Running With Buckfacebookexperimental/triton | 201 | — | ~998 | Automated safety check: Pass | MIT |
Similar skills
- Official
Install Miles Diffusion
radixark/miles_diffusion
Fallback installer for milesdiffusion on a bare CUDA 12.9 Linux GPU box, reproducing the official radixark/milesdiffusion image's package versions and verifying them.
Init GPU Server
drawthingsai/draw-things-community
Initialize a Draw Things GPU server with GPUScript, including script sync, Docker/CUDA/NVIDIA runtime setup, 7T data disk mounting, mergerfs, and end-to-end GPU verification.
- Official
Cosmos3 Setup
NVIDIA/cosmos-framework
Guide users through Cosmos3 installation, environment setup, checkpoint downloading, and verification.
- Official
Running With Buck
facebookexperimental/triton
How to build and run GPU targets under Buck in fbcode. An agent skill from facebookexperimental/triton.
- Official
Kermt Setup
NVIDIA/skills
Bootstrap the KERMT agent environment — verify host docker + nvidia-container-toolkit, build the kermt:latest image from the repo's Dockerfile if it doesn't yet exist, and run a GPU smoke test…
More from VectorSpaceLab/AREX-Skill
All 159 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents And Middleware
VectorSpaceLab/AREX-Skill
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
Related
Works with
Categories
Questions about Mining Backends
What does Mining Backends do?
Use this quip-miner sub-skill for CPU, CUDA, Metal, Modal, and QPU mining commands, backend dependencies, QPU budgets, unified streaming, and PoW/mempool scheduling. Mining Backends is an agent skill from VectorSpaceLab/AREX-Skill. Use this quip-miner sub-skill for CPU, CUDA, Metal, Modal, and QPU mining commands, backend dependencies, QPU budgets, unified streaming, and PoW/mempool scheduling.
When should I use Mining Backends?
Mining Backends fits situations like: devOps & Cloud work in your project.
How do I install Mining Backends in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill mining-backends -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends in VectorSpaceLab/AREX-Skill) into .claude/skills/mining-backends in your project. Claude Code loads it when a task matches its description.
How do I install Mining Backends in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill mining-backends -a codex`. Or copy the skill folder (skills/repositories/repo-skills/quip-miner/sub-skills/mining-backends in VectorSpaceLab/AREX-Skill) into .agents/skills/mining-backends in your project. Codex loads it when a task matches its description.
Can I use Mining Backends in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VectorSpaceLab/AREX-Skill --skill mining-backends -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mining-backends, .gemini/skills/mining-backends, .github/skills/mining-backends and .opencode/skills/mining-backends in your project.
What does Mining Backends need to run?
Going by SKILL.md and its folder, Mining Backends needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Mining Backends access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Mining Backends safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Mining Backends use?
Mining Backends is published under the AGPL-3.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Mining Backends use?
About 753 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.1k tokens, read only when the agent opens those files.
What are the alternatives to Mining Backends?
Skills that share tags, products or a category with Mining Backends: Cosmos3 Env Troubleshoot (NVIDIA/cosmos-framework, 556 stars), Install Miles Diffusion (radixark/miles_diffusion, 107 stars), Init GPU Server (drawthingsai/draw-things-community, 579 stars) and Cosmos3 Setup (NVIDIA/cosmos-framework, 556 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Mining Backends?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 328 GitHub stars. The repository holds 159 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.