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 ur-grue/autopunk-media-skills --skill document-analysis-summarygit clone --depth 1 https://github.com/ur-grue/autopunk-media-skillsWrote 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/ur-grue/autopunk-media-skills/document-analysis-summary)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/document-analysis-summary"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/document-analysis-summary/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/ur-grue/autopunk-media-skills/document-analysis-summary"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/document-analysis-summary.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 | $0.00035 | $0.01720 |
| Opus 5 | $0.00017 | $0.00860 |
| Sonnet 5 | $0.00007 | $0.00344 |
| Haiku 4.5 | $0.00003 | $0.00172 |
Grade A, and why
document-analysis-summary 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 8d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Analysis Summary
What This Skill Does
Produces a structured summary of a leaked, official, or obtained document, extracting key claims, notable gaps, internal contradictions, and the most newsworthy elements.
When To Use This Skill
- You have received a document through a FOIA response, a leak, or court discovery and need to triage its contents quickly
- You want to understand what a document does and does not say before briefing an editor
- You need to identify follow-up questions and missing records suggested by the document's content
- You are assessing whether a document corroborates, contradicts, or is irrelevant to a claim already made by a source
What You Need To Provide
Required: The full text or a detailed summary of the document; the document type (internal memo, contract, audit report, email chain, etc.); the story or investigation context Optional: Specific claims or allegations you are trying to verify or challenge; names or entities you want to cross-reference within the document; the document's provenance (how it was obtained)
How the Assistant Approaches This
- Reads the document for factual content: identifies the who, what, when, where, and any stated conclusions or recommendations
- Identifies what the document does not address — omissions that are significant given its stated purpose, gaps in dates or data, missing signatories, or redacted sections
- Flags internal contradictions — statements in different sections that conflict, discrepancies between stated figures and attached data, or language that appears to have been revised
- Ranks newsworthy elements by significance: what is new information, what confirms known facts, and what contradicts official statements
- Closes with a "Next Step" note: which follow-up document request to file first (based on the most significant finding or gap), and whether foia-request-writer or investigation-timeline-builder should be run to support the next reporting phase
Output Format
Structured summary, 400–700 words. Sections: Document Overview (type, date, author/origin, stated purpose), Key Findings (bulleted), Notable Omissions (bulleted), Internal Contradictions (bulleted, if any), Newsworthy Elements by Priority (ranked 1–5), Suggested Follow-up Documents or Questions. Neutral, factual register — no editorial framing. Output ends with a "Next Step" note: which follow-up document request to file first and whether to run foia-request-writer or investigation-timeline-builder next.
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.
- 8d ago First seen · 121 lines · 35 tokens per session scan A 6470a09a3852
document-analysis-summary is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 11d ago), licensed MIT. It adds 35 tokens to every session and 1,720 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 2026-09-04.
Other skills, from other repositories
c-research
Summarize web URLs, PDFs, YouTube videos, and podcasts using the summarize CLI. Instantly extract key points from any content type without manual reading. Useful for research, link digests, and media review.
ingest
This skill should be used when the user asks to "ingest a PDF / document", "extract text from a scanned PDF preserving page and bounding-box provenance", "convert a FOIA PDF to DoclingDocument keeping citations", "OCR a scanned document but decide native-text-vs-re-OCR first", "turn a PDF into provenance-preserving…
redaction-check
This skill should be used when the user asks to "check a PDF for bad redactions", "find improper / failed redactions", "did this FOIA response leak text under the black boxes", "is there still-extractable text under the redaction boxes", "scan a PDF for un-redacted metadata / embedded files / form values", "check my…
legal-discovery
Audit e-discovery and litigation document review systems -- data collection pipelines (PST, MBOX, SharePoint, Slack), document processing (OCR via Tesseract/ABBYY, metadata extraction, deduplication), Technology Assisted Review (TAR 1.0/2.0/CAL with recall/precision tracking).
regulatory-submissions
Audit a pharmaceutical regulatory submission system -- evaluate eCTD backbone assembly and XML validation, CTD module completeness (Modules 1-5), FDA ESG and EMA CESP gateway integration, document authoring and publishing workflows, ICH M4/M8/E3 guideline compliance.
lease-abstraction
Extract a structured abstract from a commercial lease PDF — tenant/landlord identification, premises description + RSF/USF, lease term + commencement/expiration, renewal options (count, notice windows, fair-market rent reset), base rent schedule + escalations (fixed %, CPI-linked.