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/smith-network-solutions/threadknot/pdfnpx skills add smith-network-solutions/threadknot --skill pdfgit clone --depth 1 https://github.com/smith-network-solutions/threadknotWhat 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 | $0.00088 | $0.01504 |
| Opus 5 | $0.00044 | $0.00752 |
| Sonnet 5 | $0.00018 | $0.00301 |
| Haiku 4.5 | $0.00009 | $0.00150 |
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 2d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF files
Which tool depends on the verb:
| Task | Tool |
|---|---|
| Rearrange pages, merge, split, rotate, encrypt, metadata, forms | pypdf (scripts/pdftool.py) |
| Extract text, and especially tables | pdfplumber (scripts/extract.py) |
| Make a PDF from HTML/CSS | WeasyPrint, or LibreOffice for an Office source |
| Make a PDF programmatically (precise placement) | reportlab |
| Look at a page | rasterise — scripts/extract.py --png |
Avoid PyMuPDF/fitz. It is widely recommended and technically excellent, but it is AGPL-3.0 or paid-commercial, which quietly infects whatever it touches. Everything above is MIT or BSD.
Inspect before you act
scripts/pdftool.py info report.pdf
Page count, per-page size and rotation, metadata, encryption status, whether it has form fields, and whether the pages carry extractable text or are scanned images. The last one decides your whole approach — no text extractor will get anything out of a scan, and the answer is OCR, not a different library.
Extracting text and tables
scripts/extract.py report.pdf # all text
scripts/extract.py report.pdf --pages 1-3 # a range
scripts/extract.py report.pdf --tables # tables as CSV
scripts/extract.py report.pdf --layout # preserve visual columns
--tables uses pdfplumber's ruling-line detection, which works well on tables
that have visible borders and poorly on those laid out with whitespace alone.
For the whitespace kind, --layout plus your own parsing is usually faster than
fighting the table detector.
Text comes out in the PDF's internal content order, which is not always
reading order — multi-column academic papers commonly interleave. --layout
reconstructs position-aware text and is the fix.
Scanned documents
If info reports little or no extractable text, the pages are images:
scripts/extract.py scan.pdf --ocr --pages 1-5
Needs tesseract on PATH (apt install tesseract-ocr, brew install tesseract). It rasterises each page and OCRs it. Slow — always scope with
--pages while iterating.
What ships with it
4 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.
- 2d ago First seen · 148 lines · 88 tokens per session scan A 6919b25fd6bc
pdf is a skill published in the GitHub repository smith-network-solutions/threadknot (5 stars, last pushed 8d ago), licensed Apache-2.0. It adds 88 tokens to every session and 1,504 once invoked, about $0.0004 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
reconciliation
Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.
rove
Use when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell. Also the ONLY channel for messaging another agent session on this machine — rove api send, never a peer/MCP side channel.
general-video
The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a…
motion-graphics
Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s…
release
Autonomously cut a Rove (@sma1lboy/rove) release end-to-end — detect the semver bump from pending changesets (flagging an upstream minor you didn't intend), run the release gates, bump/tag/push via scripts/release.sh, then poll the GitHub Actions Release workflow with gh until npm publish completes, diagnosing CI…
file-issue
Turn a rough idea, a bug, or a batch of unsolved problems into well-structured GitHub issue(s) and file them with gh, auto-classifying type + labels from the content (recommend, then confirm) and following Rove's conventions (beginner-friendly framing, concrete file pointers, an acceptance checklist, zero AI/Anthropic…