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 stevecrawshaw/nomis-mcp --skill nomis-extractgit clone --depth 1 https://github.com/stevecrawshaw/nomis-mcpWrote 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/stevecrawshaw/nomis-mcp/nomis-extract)<a href="https://agentmods.dev/skills/stevecrawshaw/nomis-mcp/nomis-extract"><img src="https://agentmods.dev/badge/skills/stevecrawshaw/nomis-mcp/nomis-extract.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00143 | $0.01096 |
| Opus 5 | $0.00072 | $0.00548 |
| Sonnet 5 | $0.00029 | $0.00219 |
| Haiku 4.5 | $0.00014 | $0.00110 |
Grade A, and why
nomis-extract 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NOMIS data extraction
Turn a vague data request into a confirmed spec, then download exactly that subset with the mcp__nomis__* tools. Work the steps in order. Build the spec as you go: dataset, one decision per dimension, columns, output. Call fetch_data or fetch_data_to_file only after the user has confirmed the written spec in step 5.
Read r-script.md at step 7, or whenever the user asks for an R script for NOMIS data. Read reference.md whenever the request touches geography (any area, level, "all LSOAs in X", WECA / West of England / LEP totals), the MAKE aggregate syntax, or a search_datasets error.
1. Scope: topic, geography, timescale
Ask the user about all three axes in one batch of questions. Pin every axis before searching — a wrong dataset wastes the whole chain.
- Topic — the subject and measure (counts, rates, proportions?).
- Geography — which areas, and at which level (unitary authority, LSOA, MSOA, ward, ITL2/3, region). If they name WECA, the West of England, or the LEP, read
reference.mdfor what that footprint means. - Timescale — a single latest period, a specific date, or a time series.
2. Identify the dataset
search_datasetswith a single bare keyword (claimant,earnings,population, or a census code likeTS009).reference.mdexplains why multi-word queries fail.- Prefer
status"Current (being actively updated)". get_dataset_dimensionsto confirm the dataset offers the geography level from step 1 and the breakdowns the user wants.- Tell the user the dataset id, its name, and a one-line description. Confirm it is the right one before continuing.
3. Columns: which dimensions appear in the output
- List every dimension
get_dataset_dimensionsreturned. - For each, ask the user: break it out in the output, or fix it to one value or a total?
- Ask which columns to keep. Default: date, geography name, geography code, value.
4. Filters: resolve each dimension to codes
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 65 lines · 143 tokens per session scan A 2a08eeef7cb1
nomis-extract is a skill published in the GitHub repository stevecrawshaw/nomis-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 143 tokens to every session and 1,096 once invoked, about $0.0007 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 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…