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 documentgit 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/document)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/document"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/document/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/thewolffish/wolffish-app/document"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/document.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00056 | $0.03254 |
| Opus 5.5 | $0.00022 | $0.01302 |
| Sonnet 5.5 | $0.00011 | $0.00651 |
| Haiku 4.5 | $0.00006 | $0.00325 |
Grade A, and why
document 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 1mo 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document
Interface
- Tools:
document_read,document_create,document_modify,document_template,document_convert,document_merge,document_toc,document_metadata,document_compare,document_extract_images - Supported input formats: .docx, .html, .md, .txt, .rtf
- Primary output format: .docx (create/modify/merge/template)
- All paths must be absolute. Complex parameters are JSON strings.
The shape of this capability
Two halves, like presentation.
The style engine (document_create) owns a real Word style sheet and the blocks
only reference it. That inversion is the whole difference between a document a person
can work with and one they have to fight: direct formatting cannot be restyled, does
not reach the navigation pane, and is invisible to a table of contents. Palettes are
the eight contrast-tested themes from pdf-design/themes.md, so a report, its deck and
its PDF come out of one system.
The OOXML path (read/modify/validate) works on documents the engine did not
make. find_replace is the part worth knowing about: Word splits a visible phrase
across many runs, so a naive replace matches nothing and reports success; this one
coalesces same-format runs first, then edits only inside <w:t> nodes and escapes what
it writes, because an unescaped & makes the file unopenable.
Word or PDF? If nobody will edit it, pdf_design makes a better document. Call
doc_design and it settles this first.
Rules
- Use
mammothfor reading .docx files (extracts to HTML/text). - Use
docxnpm package for creating new .docx files programmatically. - For template filling (
document_template), unzip the .docx, string-replace{{placeholders}}in the XML, and rezip. This preserves original formatting. - For
document_convertwith docx->pdf output, this capability uses the pdf capability (declared inrequires). - Support BiDi/RTL text via the docx package's bidirectional paragraph options.
- Use
os.EOLfor line endings in plain text output. - Handle EBUSY/EPERM errors gracefully (file open in another app).
What ships with it
3 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.
- 1mo ago Changed · +49 lines · +32 tokens per session 512b5842fb5a
- 1mo ago Changed · +2 lines 7f5bb9e34bb9
- 1mo ago First seen · 275 lines · 24 tokens per session scan A ead82fe5ec20
document is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed 21d ago), licensed MIT. It adds 56 tokens to every session and 3,254 once invoked, about $0.0002 per session on Opus 5.5. 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
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.
agent-computer-use
REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the agent-cu CLI commands (open, snapshot, click, type, key…
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.
papyrus-latex-suggestions
Propose inline replacement text (old -> new) as accept/reject suggestions, LaTeX 'suggesting mode' / track changes, rendered in the PDF. Use when the author wants concrete edit proposals to accept or reject. For remarks ABOUT the text rather than replacements, use papyrus-latex-comments.
create-skill
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
figma-create-design-system-rules
Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server…