local-llm-mcp-server: Skill for Claude Code

.claude/skills/artifact-first-analysis/SKILL.md

artifact-first-analysis is a skill for Claude Code from georgepok/local-llm-mcp-server. It costs 101 tokens per session (1,216 once invoked), scanned A, original, MIT.

A skeptical procedure for investigating surprising results in machine-learning experiments. It checks for data leaks, code errors, numerical problems, and evaluation flaws before interpreting what the result means.

In plain words
What is it for?
Use it before interpreting an unexpected or important experiment. It guides the investigation from possible artifacts through controlled checks and only then toward a conclusion.
Why use it?
Clean-looking results can be caused by a bug or statistical artifact rather than the mechanism being tested. This procedure helps prevent unsupported claims that a system works, fails, or has reached a limit.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is georgepok/local-llm-mcp-server's own configuration. It tells Claude Code how to work on local-llm-mcp-server 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 local-llm-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to georgepok/local-llm-mcp-server. 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/georgepok/local-llm-mcp-server/main/.claude/skills/artifact-first-analysis/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/georgepok/local-llm-mcp-server

Made for: Claude Code.

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 artifact-first-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/georgepok/local-llm-mcp-server/artifact-first-analysis/github.svg)](https://agentmods.dev/skills/georgepok/local-llm-mcp-server/artifact-first-analysis)
Your own site
<a href="https://agentmods.dev/skills/georgepok/local-llm-mcp-server/artifact-first-analysis"><img src="https://agentmods.dev/badge/skills/georgepok/local-llm-mcp-server/artifact-first-analysis/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 artifact-first-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/georgepok/local-llm-mcp-server/artifact-first-analysis"><img src="https://agentmods.dev/badge/skills/georgepok/local-llm-mcp-server/artifact-first-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,216 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.
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 $0.00101 $0.01216
Opus 5 $0.00051 $0.00608
Sonnet 5 $0.00020 $0.00243
Haiku 4.5 $0.00010 $0.00122

Measured 9d ago against content hash 4c2d5b5f8b37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

artifact-first-analysis 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 9d 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.

.claude/skills/artifact-first-analysis/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Artifact-First Analysis

You are a skeptical mechanistic-interpretability researcher. Treat every unexpected model behavior as a software bug or statistical artifact until proven otherwise. Interpretation is the LAST step, never the first. Execute in order; do not skip.

0. Freeze interpretation

The moment you notice yourself narrating what a result "means" (the model reasons / remembers / a boundary is reached / the approach is exhausted), STOP. That sentence is a hypothesis to be attacked, not a conclusion. Write it down as the thing to disprove.

The mandatory ordered protocol (execute 1→6 in order, never skip ahead)

1. Artifact hypothesis first. List ≥3 concrete ways the result is an artifact — do NOT interpret meaning yet:

  • Data leakage — target reachable without the mechanism (label in prompt, train/test overlap, ordering, tokenizer quirk).
  • Code/graph bug — stop-grad, wrong slice/index, eval≠train path, hook not firing, wrong layer/module, dtype/device mismatch, intervention silently a no-op.
  • Numeric — under/overflow, fp16/bf16 saturation, a loss pinned at a constant (ln(2)≈0.693 ⇒ two logits equal; ln(N) ⇒ uniform).
  • Evaluation flaw — metric measures label frequency / base rate; small-n quantization; greedy+fixed-seed determinism; teacher-forcing hiding a generation failure; contaminated baseline.
  • Invariance sub-check: predict how the number MUST move under a trivial change (seed; label/target set) and test one. Exact repetition to 2–3 decimals across genuinely different configs is NOT robustness — it is the fingerprint of an inert path (mechanism not in the causal chain). Verify the intervention changes activations at all.

2. Constant-baseline check. Compute the trivial baselines and print them NEXT TO the metric: majority-class / "always predict the modal token" accuracy, and the intervention-OFF accuracy. If your number ≈ a constant baseline, you have measured nothing.

3. Correct-vs-wrong state check. Re-run with the mechanism's input SCRAMBLED (wrong instance's state, shuffled, or noise), everything else identical. Report Δ = acc(correct) − acc(wrong) and the fraction of predictions that change when you swap. Δ≈0 / no change ⇒ the content is causally inert. Distinguish presence-effect (ON vs OFF changes output) from content-effect (changing WHAT it carries changes output) — presence ≠ content.

Read the full file on GitHub · 84 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. 9d ago First seen · 84 lines · 101 tokens per session scan A 4c2d5b5f8b37

Subscribe to this mod's changes

artifact-first-analysis is a skill published in the GitHub repository georgepok/local-llm-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 1,216 once invoked, about $0.0005 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 2026-09-01.

Related

Other skills, from other repositories

arboreto

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…

K-Dense-AI/scientific-agent-skills · 66 tokens

pyhealth

Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…

K-Dense-AI/scientific-agent-skills · 216 tokens

torchdrug

Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.

K-Dense-AI/scientific-agent-skills · 61 tokens

deepspot-m

Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…

K-Dense-AI/scientific-agent-skills · 80 tokens

nemo-mbridge-perf-expert-parallel-overlap

Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.

NVIDIA/skills · 56 tokens

pick-a-pii-model

Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.

maziyarpanahi/openmed · 64 tokens