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 brightwave-inc/tidebreak --skill word-documentsgit clone --depth 1 https://github.com/brightwave-inc/tidebreakWrote 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/brightwave-inc/tidebreak/word-documents)<a href="https://agentmods.dev/skills/brightwave-inc/tidebreak/word-documents"><img src="https://agentmods.dev/badge/skills/brightwave-inc/tidebreak/word-documents.svg" alt="Measured on agentmods" 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 | $0.01717 |
| Opus 5 | $0.00017 | $0.00859 |
| Sonnet 5 | $0.00007 | $0.00343 |
| Haiku 4.5 | $0.00003 | $0.00172 |
Grade A, and why
word-documents 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Word documents
Two paths produce a DOCX, and picking the wrong one destroys work. Choose first, then follow that path's section, and finish with the validation section — it applies to both.
Which path
- An existing
.docxis in play — a template, a document the user uploaded, a prior version of this deliverable, a downloaded starting point — edit it in place with the XML pipeline below. Always. - Nothing exists yet and there is no template — build the document from scratch with python-docx.
Never rebuild an existing document with python-docx to apply a change.
Document() starts from the library's default template, and it cannot
reproduce a firm's: the style definitions, numbering, headers and footers,
theme fonts, and page setup all come back as generic defaults, so
regenerating silently strips the design the user is attached to. A one-line
text fix is a one-line XML edit, not a rewrite. Equally, never recreate from
scratch what a template already provides — if the user handed you a template,
its design is the requirement.
When DOCX is the right format
Reach for DOCX when the user will edit, print, or share the document in Word — a report, letter, proposal, or anything with real formatting. When the user just needs readable text they will consume in the chat or a plain file, a markdown output serves them better than a DOCX: say so and offer the simpler format instead of defaulting to Word.
New documents: python-docx
Install the pinned dependency with its own exec call — commands have a
bounded wall clock, and one pip invocation per package stays inside it:
python3 -m pip install --user python-docx==1.1.2
Installs work only when this chat's network policy allows package managers, and they persist for the rest of the conversation. If an install is refused by policy, do not retry: tell the user to enable the package-manager network policy for this chat, and offer the closest format you can produce without the library (markdown or HTML) — only with their knowledge, never as a silent substitution. If a dependency cannot be installed at all, say so plainly instead of quietly delivering a lesser format.
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 · 138 lines · 35 tokens per session scan A bc49ef7c4e97
word-documents is a skill published in the GitHub repository brightwave-inc/tidebreak (24 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 1,717 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 2026-08-30.
Other skills, from other repositories
stack-trace-rust-probe
Internal helper for meta-stack-trace-investigator. Use when a Rust panic or backtrace needs Rust-specific Result/Option checks, cargo test guidance, and patch targets.
ax-rust-llm
Use when writing Rust code with axllm for using the generated Ax package, factory functions, package docs, examples, and API reference.
ax-rust-signature
Use when writing Rust code with axllm for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.
tencent-docs
A skill for creating, reading, editing, searching, and managing Tencent Docs, an online document and spreadsheet service.
government-writing
A skill for writing formal Chinese government documents, including notices and opinions, in the required official format.
ima-skills
Tencent IMA OpenAPI skill for notes and knowledge-base operations. Use after the user connects IMA in Pinvou Plugin Center.