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 TimSimpsonJr/magpie --skill analysis-recipegit 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/analysis-recipe)<a href="https://agentmods.dev/skills/timsimpsonjr/magpie/analysis-recipe"><img src="https://agentmods.dev/badge/skills/timsimpsonjr/magpie/analysis-recipe/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/timsimpsonjr/magpie/analysis-recipe"><img src="https://agentmods.dev/badge/skills/timsimpsonjr/magpie/analysis-recipe.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00108 | $0.02262 |
| Opus 5 | $0.00054 | $0.01131 |
| Sonnet 5 | $0.00022 | $0.00452 |
| Haiku 4.5 | $0.00011 | $0.00226 |
Grade A, and why
analysis-recipe 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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
analysis-recipe
Run Magpie's repeatable investigative pass: a fixed, parameterized 13-point
checklist applied identically to one FOIA / audit-log source, then a
cross-source rollup that tests whether patterns and actors recur across
sources. This is the Track A flagship's analysis layer — it sits on top of
dataset-analyze (which loads, quality-gates, and derives each source) and feeds
its findings to Librarian.
Two deterministic scripts do the work; the agent orchestrates the fan-out:
scripts/recipe.py::run_recipe(df, config)— the per-source 13-point pass.scripts/rollup.py::rollup(findings_list)— the cross-source synthesis.
Both are pure and golden-tested. The verified-API contract and the exact
findings / check / rollup schemas live in references/prior-art.md (the Phase 4
research gate) — consult §3 before changing a call or a config key.
Per-source pass
For each source, first produce a clean, derived DataFrame via the
dataset-analyze pipeline (load → data-quality gate → derive: geo,
reason_cat/reason_text, is_immigration, nets, has_case, base_type,
date_et/hour_et). Then run the recipe:
from scripts.recipe import run_recipe
config = {
"source_id": "simpsonville-network-audit",
"checks": {
"truncation": {},
"out_of_state": {"geo_col": "geo", "out_label": "OOS", "unknown_label": "UNK"},
"immigration": {"text_col": "reason_text", "keywords": ["ice", "immigration", "deportation", "cbp"]},
"pretext": {"text_col": "reason_text", "keywords": ["traffic", "registration", "equipment"]},
"pii": {"text_cols": ["reason_text"]},
"accountability": {"case_col": "has_case", "group_col": "geo"},
"co_travel": {"text_col": "reason_text", "keywords": ["convoy", "co-travel", "caravan"]},
"blast_radius": {"nets_col": "nets", "severity_col": "base_type"},
"mega_users": {"user_col": "agency"},
"operations": {"user_col": "agency", "date_col": "date_et", "hour_col": "hour_et"},
"ai_moderation": {"hour_col": "hour_et", "user_col": "agency", "timestamp_col": "ts"},
"cross_agency": {"user_col": "agency", "external_geo_col": "geo", "external_label": "OOS"},
"statistical_patterns": {"user_col": "agency"},
},
}
findings = run_recipe(df, config)
What ships with it
1 file 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.
- 9d ago First seen · 163 lines · 108 tokens per session scan A 23a48fc684af
analysis-recipe is a skill published in the GitHub repository TimSimpsonJr/magpie (2 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 2,262 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.
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.
osint-tool-catalog
Produces a categorised catalog of open-source intelligence tools relevant to a journalist's investigation, with practical guidance on what each tool does, when to use it, and what its limitations are.
social-media-intelligence
Produces a structured open-source intelligence brief on a social media account or set of accounts, covering account authenticity analysis, narrative tracking, and coordination-detection patterns to support investigative reporting.
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.
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.