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/docxnpx skills add smith-network-solutions/threadknot --skill docxgit 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 | $0.00102 | $0.01643 |
| Opus 5 | $0.00051 | $0.00822 |
| Sonnet 5 | $0.00020 | $0.00329 |
| Haiku 4.5 | $0.00010 | $0.00164 |
Grade A, and why
docx 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Word documents (.docx)
A .docx is a ZIP archive of XML parts. Two ways in, and picking the right one
is most of the job:
| Need | Route |
|---|---|
| Write a document, edit text, add tables/images/styles | python-docx (scripts/ here) |
| Tracked changes, comments, footnotes, content controls, anything python-docx has no API for | raw OOXML — scripts/ooxml.py unpack, edit the XML, pack |
Never hand-write a whole .docx as XML from nothing. Start from a real file —
either one python-docx produced or one the user supplied — and modify it.
Before editing an existing file, look at it
scripts/inspect_docx.py report.docx
Prints every paragraph with its index and style, every table with its dimensions, section/page setup, headers and footers, and the document's declared styles. Do this first on any file you did not create. Paragraph indices from this listing are what the editing recipes below address.
Creating a document
Write a short Python script using python-docx. The API worth remembering:
from docx import Document
from docx.shared import Pt, Inches, RGBColor
from docx.enum.text import WD_ALIGN_PARAGRAPH
doc = Document() # or Document("template.docx") to build on one
doc.add_heading("Quarterly Report", level=1)
p = doc.add_paragraph("Ordinary body text. ")
run = p.add_run("Bold tail.") # runs carry the character formatting
run.bold = True
p.alignment = WD_ALIGN_PARAGRAPH.JUSTIFY
table = doc.add_table(rows=1, cols=3)
table.style = "Table Grid" # without a style the table has NO borders
hdr = table.rows[0].cells
hdr[0].text, hdr[1].text, hdr[2].text = "Region", "Q1", "Q2"
for region, q1, q2 in data:
cells = table.add_row().cells
cells[0].text = region
cells[1].text = f"{q1:,.0f}"
doc.add_picture("chart.png", width=Inches(6))
doc.add_page_break()
doc.save("report.docx")
Points that cost time if you learn them the hard way:
- All measurements are typed.
Pt,Inches,Cm,Emu— never a bare number. Internally everything is EMU (914400 per inch). - Formatting lives on runs, not paragraphs.
paragraph.text = "x"destroys the paragraph's runs and their formatting. To change text while keeping formatting, assign torun.texton the existing runs. - A table with no
.stylehas no visible borders."Table Grid"is the usual intent. - Styles must already exist in the document. Building on a user's template
inherits their styles;
Document()gives you the default set. Check withinspect_docx.pybefore referencing a style by name. add_heading(level=0)produces a Title, not a heading.
What ships with it
5 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 · 157 lines · 102 tokens per session scan A 5d58611d01b5
docx is a skill published in the GitHub repository smith-network-solutions/threadknot (5 stars, last pushed 8d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,643 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
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…
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…
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…