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.
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.
curl -O https://raw.githubusercontent.com/Mesh-LLM/mesh-llm/main/.agents/skills/skippy-spec-bench/SKILL.mdgit clone --depth 1 https://github.com/Mesh-LLM/mesh-llmWrote 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/mesh-llm/mesh-llm/skippy-spec-bench)<a href="https://agentmods.dev/skills/mesh-llm/mesh-llm/skippy-spec-bench"><img src="https://agentmods.dev/badge/skills/mesh-llm/mesh-llm/skippy-spec-bench/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/mesh-llm/mesh-llm/skippy-spec-bench"><img src="https://agentmods.dev/badge/skills/mesh-llm/mesh-llm/skippy-spec-bench.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 | $0.00036 | $0.00218 |
| Opus 5 | $0.00018 | $0.00109 |
| Sonnet 5 | $0.00007 | $0.00044 |
| Haiku 4.5 | $0.00004 | $0.00022 |
Grade A, and why
skippy-spec-bench 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 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.
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.
What it actually says
skippy-spec-bench
Use this skill for target/draft speculative compatibility work.
What It Checks
- Target and draft tokenization agreement.
- Baseline target decode versus draft-verified decode.
- Draft acceptance/rejection behavior.
- Batched verification and checkpoint/restore behavior.
- Recurrent-state implications for rollback.
Repo Notes
The old source repo used a standalone llama-spec-bench crate. It may not be
present in this mesh checkout yet, so verify available packages before running
commands:
cargo metadata --no-deps --format-version 1 | jq -r '.packages[].name' | sort
If the spec bench is imported, keep it as a diagnostics/benchmark tool. Do not make normal mesh serving depend on it.
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 · 32 lines · 36 tokens per session scan A 6dae350ea409
skippy-spec-bench is a skill published in the GitHub repository Mesh-LLM/mesh-llm (3,371 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 218 once invoked, about $0.0002 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.
Other skills, from other repositories
test
Enter the Test phase of CocoBrew. Reads spec.md test requirements, generates test cases, executes SQL validation and quality checks, records results in test.md. Can be re-run without full rebuild. Requires Build phase completion.
examples-qa
Verify Instructor behavior through the repository's ./examples/ suite in pass, live record, or hermetic replay mode. Use when running selected examples or the corpus, capturing and reusing recorded LLM HTTP responses, diagnosing hub results, or distinguishing real errors, assertion failures, skipped examples, and…
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.
golden-dataset
Golden dataset lifecycle patterns for curation, versioning, quality validation, and CI integration. Use when building evaluation datasets, managing dataset versions, validating quality scores, or integrating golden tests into pipelines.
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…