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 LegalQuants/lq-skills --skill superdoc-redlinesgit clone --depth 1 https://github.com/LegalQuants/lq-skillsWrote 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/legalquants/lq-skills/superdoc-redlines)<a href="https://agentmods.dev/skills/legalquants/lq-skills/superdoc-redlines"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/superdoc-redlines/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/legalquants/lq-skills/superdoc-redlines"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/superdoc-redlines.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 | $0.00040 | $0.00987 |
| Opus 5 | $0.00020 | $0.00494 |
| Sonnet 5 | $0.00008 | $0.00197 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
superdoc-redlines 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 12d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
superdoc-redlines — Multi-Agent DOCX Redlining
When to Use
- Multi-agent legal workflows where different agents produce edits to the same document
- Applying AI-generated tracked changes to DOCX files
- Merging edits from multiple reviewers with conflict resolution
- Headless document transformation (no Word installation required)
- Deterministic document edits with stable block IDs
How It Works
Core Innovation
Uses stable block IDs instead of fragile text matching. Unlike approaches that try to find text by content (and fail when formatting changes), Superdoc assigns stable IDs to document blocks and applies changes by reference.
Architecture
AI Agent output → Conflict resolution → Block ID mapping → Native Word revisions
Process
- Parse — Extract document blocks with stable IDs
- Receive edits — AI agent produces change instructions
- Conflict resolution — If multiple agents edit same block, resolve conflicts
- Apply — Insert Word tracked changes using block IDs (not text matching)
- Output — Native DOCX with Word revision marks
Usage
import { applyRedlines } from 'superdoc-redlines';
const result = await applyRedlines({
input: './contract.docx',
edits: agentEdits,
agentName: 'Claude'
});
Key Features
- Multi-agent merging — Multiple agents can edit; conflicts are flagged
- Conflict resolution — Human review for overlapping edits
- Deterministic — Same edits → same output (unlike text-matching approaches)
- Native Word revisions — Output is valid DOCX, not a proprietary format
- Works headlessly — No Word installation needed
Audience and Work Shape
Audience: lawyers and developers running multi-agent DOCX workflows where several AI agents propose edits to the same document. The lawyer is the merger of last resort.
Work shape: Bounded Transactional with conflict-resolution overlay. The skill merges defined edits by stable block ID. Conflicts are surfaced, not silently resolved.
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.
- 12d ago First seen · 106 lines · 40 tokens per session scan A d2e7e41e321e
superdoc-redlines is a skill published in the GitHub repository LegalQuants/lq-skills (54 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 987 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
docx-press
Teaches agents how to author Markdown that renders cleanly into DOCX via writedocx, with heading hierarchy (up to 6 levels), tables, lists, blockquotes, code blocks, citations, embedded images, SVG diagrams (rendered to PNG first), and document structure patterns for reports, proposals, and technical documents.
deckprobe
Inspect PDF, Microsoft Office (docx/xlsx/pptx and legacy doc/xls/ppt), and Apple iWork (key/numbers/pages) files without opening or rendering them. Use for page and slide and sheet counts, title/author/created metadata, encryption and macro and digital-signature and JavaScript risk signals, sheet and table structure…
法律文件脱敏处理
A browser-based and Python tool for removing sensitive details from legal Word documents and restoring them later. It can replace information such as names, dates, prices, bank accounts and case numbers while preserving document formatting.
llm-wiki-builder
Build or refresh Foam-compatible LLM wikis from Asset-Aware documents, citation bundles, tables, figures, and local Markdown notes using a multi-tool workflow.
docx-batch-variable-replacement
A document-processing tool that copies a Word template and replaces specified placeholders or details in each generated file.
anywrite
Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.