mesh-llm: Skill for Claude Code

.agents/skills/skippy-prompt/SKILL.md

skippy-prompt is a skill for Claude Code, Codex from Mesh-LLM/mesh-llm. It costs 82 tokens per session (1,044 once invoked), scanned A, original, Apache-2.0.

A workflow skill for running and diagnosing Skippy’s staged serving and prompt tools across local or remote machines. Staged serving splits model work between ordered processing stages.

In plain words
What is it for?
Use it to migrate prompt-owned serving, sync code to lab nodes, build runtimes, start stage servers, and operate the prompt client.
Why use it?
It coordinates hosts, builds, backends, configuration, startup, observation, and cleanup so prompt-based runtime checks follow the project’s rules.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is Mesh-LLM/mesh-llm's own configuration. It tells Claude Code and Codex how to work on mesh-llm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mesh-llm configures →

About the project

Mesh LLM is a distributed AI system that combines GPUs and memory from multiple machines and exposes them through one OpenAI-compatible inference server, which is a service that runs models and answers API requests. It is for people who want to share compute privately or publicly to run models for agents and chat, including models too large for one machine. The catalogue add-ons support workflows for operating and using the mesh.

Mesh-LLM/mesh-llm · 3,384 stars · on GitHub · meshllm.cloud

Reuse

Borrowing it

Nothing to install: this file belongs to Mesh-LLM/mesh-llm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Mesh-LLM/mesh-llm/main/.agents/skills/skippy-prompt/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Mesh-LLM/mesh-llm

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for skippy-prompt

README.md
[![agentmods](https://agentmods.dev/badge/skills/mesh-llm/mesh-llm/skippy-prompt/github.svg)](https://agentmods.dev/skills/mesh-llm/mesh-llm/skippy-prompt)
Your own site
<a href="https://agentmods.dev/skills/mesh-llm/mesh-llm/skippy-prompt"><img src="https://agentmods.dev/badge/skills/mesh-llm/mesh-llm/skippy-prompt/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.

agentmods 80×15 button for skippy-prompt

Your own site · 80×15
<a href="https://agentmods.dev/skills/mesh-llm/mesh-llm/skippy-prompt"><img src="https://agentmods.dev/badge/skills/mesh-llm/mesh-llm/skippy-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,044 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.01044
Opus 5 $0.00041 $0.00522
Sonnet 5 $0.00016 $0.00209
Haiku 4.5 $0.00008 $0.00104

Measured 12d ago against content hash 7e5dcb294704, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

skippy-prompt 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 12d 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.

.agents/skills/skippy-prompt/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skippy-prompt

Use this skill for prompt-owned staged workflows. The skill is the launcher: Codex orchestrates sync, host-native builds, stage config generation, process startup, observation, prompt driving, and teardown.

Ownership Rules

  • The machine where the user asks to launch prompt is always stage-0.
  • Remote hosts are stage-1..N in the order provided by the user.
  • Bring down any running mesh-llm serving on the chosen nodes before starting prompt-owned stage servers.
  • Do not bring back standalone kv-server or ngram-pool.
  • Use $HOME/tmp for run roots, source syncs, logs, and bundles. Avoid /tmp unless the user explicitly asks for it.
  • Public OpenAI compatibility belongs in openai-frontend, not prompt tooling. Prompt workflows are for development, diagnostics, and reproducible model checks.
  • Do not use skippy-prompt prompt as the launcher on this branch. The skill starts skippy-server serve-binary stages directly and uses skippy-prompt binary as the interactive client.

Launch Workflow

  1. Confirm repo state, branch, commit, model ref/path, hosts, desired layer ranges, context size, and prompt mode.
  2. Stop existing mesh/runtime processes on every selected host: mesh-llm stop first, then verify with ps; use pkill -f only if the scoped stop path fails.
  3. Rsync the current source tree to each remote host under $HOME/tmp/mesh-llm-prompt-src/<branch-or-sha>/, excluding build outputs and caches (target/, .git/, .deps/llama-build/, UI node_modules/).
  4. Detect each host: uname -s, uname -m, GPU inventory, compiler/runtime availability, and existing llama build cache.
  5. Choose the best backend per host:
    • macOS: Metal.
    • Linux NVIDIA with CUDA toolchain: CUDA. Use this for white.local unless CUDA is genuinely unavailable.
    • Linux AMD with ROCm toolchain: ROCm.
    • Vulkan-capable Linux without CUDA/ROCm: Vulkan.
    • CPU only as a last resort or explicit user request.
  6. Build on each host with repo-native just targets. Use just build on macOS and just build-runtime backend=<backend> ... on Linux when UI rebuild is unnecessary. Do not hand-roll cargo/cmake build sequences.
  7. Materialize or locate model/package inputs on the launcher. If the source model only exists locally, rsync package/materialized stage inputs to remote hosts.
  8. Start final stage first, then upstream stages, ending with local stage-0. Use foreground TTY SSH for first repro/debug runs and tee logs under $HOME/tmp/skippy-prompt-runs/<run-id>/.
  9. Wait for readiness of every stage, then attach skippy-prompt binary from the launcher to the local stage-0 endpoint.
  10. Keep process handles or SSH sessions observable. Do not report success until stage servers are running and a prompt request has been attempted or the user explicitly only asked for startup.

Read the full file on GitHub · 103 lines

Changes

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.

  1. 12d ago First seen · 103 lines · 82 tokens per session scan A 7e5dcb294704

Subscribe to this mod's changes

skippy-prompt is a skill published in the GitHub repository Mesh-LLM/mesh-llm (3,384 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 1,044 once invoked, about $0.0004 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 2026-08-30.