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 thewolffish/wolffish-app --skill pdfgit clone --depth 1 https://github.com/thewolffish/wolffish-appWrote 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/thewolffish/wolffish-app/pdf)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/pdf"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/pdf.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 | $0.00018 | $0.04775 |
| Opus 5 | $0.00009 | $0.02388 |
| Sonnet 5 | $0.00004 | $0.00955 |
| Haiku 4.5 | $0.00002 | $0.00477 |
Grade A, and why
pdf 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 — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading and querying PDFs — especially huge ones
Attached PDFs are NEVER auto-loaded into your context — every one arrives as a note with the
path and page count, and even a 2-page PDF must be read with pdf_read before you can speak
about its contents. That is deliberate (100% model-led file access): a 3,000-page PDF extracts
to millions of tokens — no context window holds it — so YOU control what to load and when.
The reading tools make the entire document reachable surgically, and you are expected to
actually use them:
pdf_infofirst for anything nontrivial: page count, outline with page numbers, and text density. A density warning means a scanned/image PDF — say so plainly instead of pretending to read it.- Targeted questions →
pdf_search, not paging. It scans every page in scope and reports the authoritative total. Search several phrasings/synonyms before concluding something is absent ("termination", "cancel", "wind-down" — not just one term). Thenpdf_readthe matching pages with a few pages of surrounding context. - Whole-document tasks (summaries, audits, reviews) → systematic traversal. Work through
the document in page ranges (
"1-40","41-80", …), keeping running notes withfile_writeas you go for anything beyond a few hundred pages, then synthesize from your notes. The per-call cap tells you exactly where to continue; nothing is ever silently dropped. - Never claim coverage you did not do. Do not say "the document states/doesn't mention X" unless you read the relevant pages or searched exhaustively for X and its synonyms. If you only sampled, say which pages you actually consulted.
- Narrate while you dig — the user cannot see your tool calls. Before the first search of a big document, say so in one line (the one-time extraction can take a while: "Searching the book — first pass extracts it once, may take a minute…"). Between search/read rounds, drop a one-line finding ("dosing table on p. 497 — checking renal adjustment next"). Silent digging looks like a hang, no matter how well it's going.
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.
- 8d ago First seen · 423 lines · 18 tokens per session scan A 10a66314c567
pdf is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 4,775 once invoked, about $0.0001 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
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
paper-figures
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACTFIGURES}} — use…
pdf-reader
Extract text from PDF files. Use when reading, parsing, or analyzing PDFs.
moai-docs-generation
Documentation generation patterns for technical specs, API docs, user guides, and knowledge bases using real tools like Sphinx, MkDocs, TypeDoc, and Nextra. Use when creating docs from code, building doc sites, or automating documentation workflows.
doc-ingest
Extract readable text from document files — PDF, XLSX/CSV/TSV, DOCX, PPTX, and plain-text formats — so any task that arrives with an attachment can actually consume it.