SurfSense is an open-source desktop application that uses an AI agent to research, transform, and edit documents while keeping their index on the user's machine. It is intended for people working with documents they cannot upload, with a choice of local or remote models and no account required.
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 MODSetter/SurfSense --skill docxgit clone --depth 1 https://github.com/MODSetter/SurfSenseWrote 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/modsetter/surfsense/docx)<a href="https://agentmods.dev/skills/modsetter/surfsense/docx"><img src="https://agentmods.dev/badge/skills/modsetter/surfsense/docx/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/modsetter/surfsense/docx"><img src="https://agentmods.dev/badge/skills/modsetter/surfsense/docx.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.00662 |
| Opus 5.5 | $0.00009 | $0.00265 |
| Sonnet 5.5 | $0.00004 | $0.00132 |
| Haiku 4.5 | $0.00002 | $0.00066 |
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 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DOCX
Create the requested Word document in /workspace with the preinstalled
python-docx package. Never install or download dependencies.
Authoring rules
- Use one page size and orientation for the document unless the user asks for a different layout. Prefer portrait; narrow wide content instead of silently switching sections to landscape.
- Choose the page size the user requests, or the locale-appropriate default when they do not specify one.
- Set margins of at least 18 mm and use built-in heading levels.
- Set table and cell widths deliberately and use a visible table grid.
- Use Word numbering/list styles; never insert literal
•characters. - Put page breaks in their own paragraphs. Use separate paragraphs instead of newline characters for separate blocks.
- Do not add a table of contents unless the user asks. If requested, use built-in heading levels and state that page numbers populate when Word opens and updates the field.
- For right-aligned text on the same line, use a right tab stop.
- Generate the document as one whole document. Do not assemble or save one DOCX per intended page; Word controls pagination through reflow.
Revisions
Start an in-place revision with load_artifact_for_revision. Use
python-docx to open primary_path, make common edits directly to the existing
document, and write the result to expected_output_path. Common edits include
paragraph text and styles, headings, ordinary tables, lists, headers/footers,
section settings, and embedded images that python-docx can safely preserve.
If the requested edit touches a structure python-docx cannot safely interpret
or preserve—such as macros, SmartArt, complex fields, tracked changes, content
controls, or unsupported drawing/layout XML—stop and report the blocker. Do not
silently rebuild from markdown_path and do not fall back to a Markdown-only
deliverable. Rebuild the DOCX from Markdown/context only when the user
explicitly requested or accepted that lossy rebuild.
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 eac098d1a26e
- 1mo ago First seen · 62 lines · 22 tokens per session scan A 78025438d67b
docx is a skill published in the GitHub repository MODSetter/SurfSense (16,599 stars, last pushed yesterday), licensed Apache-2.0. It adds 22 tokens to every session and 662 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
leiloeiro-edital-ranbot-ai
Analise e auditoria de editais de leilao judicial e extrajudicial. Riscos ocultos, clausulas perigosas, debitos, ocupante e classificacao da oportunidade.
first-reader
Beta readers for any draft, run by simulating how a real reader experiences it, moment by moment. A skim gate, a no-lookahead timed read producing an attention transcript with quit points, a recall test of what a reader remembers the next day, and a trust ledger of the implied author. Use when the user asks for a beta…
mcp-apps-builder
MANDATORY for ALL MCP server work - mcp-use framework best practices and patterns. READ THIS FIRST before any MCP server work, including: Creating new MCP servers Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) Debugging MCP server issues or errors Reviewing MCP server code for…
project-graveyard
Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…
commit-archaeologist
Reconstructs why code exists from local git history, including the introducing commit, later changes, current authors, repeated companion files, and likely intent. Use when the user asks "why does this code exist", "who wrote this function and why", or to "explain the history of this function" before a rewrite…
dependency-doctor
Checks requirements.txt, pyproject.toml, and package.json dependency manifests for surface-level direct-dependency footguns: standard-library shadowing pins, abandoned backports, unpinned dependencies, and obvious intra-manifest conflicts, plus opt-in PyPI yanked releases. Use when the user asks to check a manifest…