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 agentmods add skills/timsimpsonjr/magpie/setupnpx skills add TimSimpsonJr/magpie --skill setupgit clone --depth 1 https://github.com/TimSimpsonJr/magpieWrote 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/timsimpsonjr/magpie/setup)<a href="https://agentmods.dev/skills/timsimpsonjr/magpie/setup"><img src="https://agentmods.dev/badge/skills/timsimpsonjr/magpie/setup.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 | $0.00098 | $0.01541 |
| Opus 5 | $0.00049 | $0.00771 |
| Sonnet 5 | $0.00020 | $0.00308 |
| Haiku 4.5 | $0.00010 | $0.00154 |
Grade A, and why
setup 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 4d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The setup skill is the operator's one-time onramp: it brings a fresh machine from
nothing to a working Magpie install and then proves what is ready. It is driven by
the shared capability engine scripts/detect_tier.py, which probes the toolchain
(installed distributions, the spaCy model, the system binaries, and the mcp-sqlite
wiring) with no heavy imports and no side effects, and reports a per-capability map
in plain user verbs. Setup is the only Magpie skill that MAY install; its read-only
sibling is doctor.
1. What setup does
Setup runs scripts/detect_tier.py to see the current state, installs the missing
pieces it is allowed to install (with the operator present and consenting), instructs
the operator for the pieces pip cannot manage, and re-runs scripts/detect_tier.py
to report the now-current capability map. It is meant to be run by an operator on the
machine, once, during onboarding (or again later to repair a gap doctor flagged).
2. The flow
a. Probe first. Run scripts/detect_tier.py and SHOW the operator what is present
versus missing, capability by capability, before changing anything.
b. Bootstrap the Python side. With the operator present and consenting, run
mise run bootstrap. That installs the pinned pip dependencies and the
en_core_web_lg spaCy wheel into the project venv. (The Docling and RapidOCR model
weights are not downloaded here; they fetch on the first ingest run.) Bootstrap
also installs the Track-B entity-extract models gliner and glirel; like Docling,
their weights download on first use. NOTE the license: the GLiREL relation-model
weights are CC BY-NC-SA 4.0 (non-commercial) -- the user downloads them (not
vendored) and Magpie's MIT code is unaffected. The FtM/graph layer
(followthemoney/nomenklatura) is Linux/CI only and is NOT installed on Windows
(PyICU has no Windows wheel), so on Windows the entity-extract deliverable is the
reviewed intermediate. In the -NoProfile PowerShell shell, bare python is the
wrong interpreter, so the fallback that does the same install is:
& .venv\Scripts\python.exe -m pip install -r requirements-dev.txt
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.
- 4d ago First seen · 102 lines · 98 tokens per session scan A 28bbbe77af7c
setup is a skill published in the GitHub repository TimSimpsonJr/magpie (2 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 1,541 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 2026-08-31.
Other skills, from other repositories
pdf-table-extractor-brief
Produces a structured extraction plan and clean spreadsheet template for pulling tabular data out of a PDF document — identifying the table structure, defining column headers, flagging extraction pitfalls, and providing a ready-to-use template that ensures the data lands in a consistent, analysable format.
data-cleaning-brief
Writes clear, step-by-step instructions for cleaning a messy or inconsistent dataset — specifying exactly what needs to be standardised, corrected, or removed to make the data ready for analysis and publication.
data-outlier-finder
Identifies unusual values, unexpected patterns, and potential stories hidden in a dataset by systematically checking for statistical outliers and contextual anomalies.
foi-data-request
Drafts a Freedom of Information request specifically targeting datasets, databases, or digital records — written to maximise the chance of receiving complete, machine-readable data rather than summary PDFs or partial tables.
scraper-brief
Writes a clear, technical brief describing exactly what data needs to be collected from a website or set of web pages, how it should be structured, and what edge cases and legal/ethical considerations apply — for handoff to a developer or data team.
foia-request-writer
Drafts legally complete public records requests (federal FOIA and all 50 state laws), administrative appeals, and redaction challenge strategies for U.S. government records.