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 collating-reviewer-feedbackgit 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/collating-reviewer-feedback)<a href="https://agentmods.dev/skills/legalquants/lq-skills/collating-reviewer-feedback"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/collating-reviewer-feedback/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/collating-reviewer-feedback"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/collating-reviewer-feedback.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 | $0.00060 | $0.01512 |
| Opus 5 | $0.00030 | $0.00756 |
| Sonnet 5 | $0.00012 | $0.00302 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
collating-reviewer-feedback 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
collating-reviewer-feedback
When to Use
- Multiple reviewers returned Word documents with comments or tracked changes.
- The team needs to see every proposed edit, comment, and conflict in one place.
- The master document is court-facing, client-facing, or otherwise too risky to auto-merge.
- Feedback arrived outside Word, such as email, Teams, WhatsApp, phone notes, or conference comments, and needs to be added to the same resolution list.
Do not use this skill to automatically accept, reject, or merge changes into the master document. The output is a review checklist. The lawyer makes every document edit.
Audience and Work Shape
Audience: drafting and litigation lawyers, trainees, and paralegals who own or support the master document and understand Word comments/track changes.
Work shape: pattern-matched review with bounded extraction. The skill compiles, groups, and classifies reviewer inputs; it does not decide the legal or drafting outcome.
Legal Failure Modes
- Legal support, not legal advice: the checklist is a review aid. The responsible lawyer decides whether and how to amend the master.
- Privilege/confidentiality: privileged or confidential drafts must be processed only in an approved environment. Uploading drafts or extracted comments to an unapproved third-party AI surface may affect privilege or confidentiality.
- Accountability: every item defaults to
openorunresolved; a lawyer owns each accept/reject/defer decision.
Access Modes
This skill works in two practical modes:
- File mode - use uploaded or accessible DOCX files, reviewer versions, exports, or extracted Word markup.
- User-supplied text mode - use pasted comments, exported revision tables, screenshots, email notes, or manually supplied feedback.
If reviewer files or extracted markup are unavailable, prepare an intake checklist and do not claim to have collated Word comments or track changes.
How It Works
1. Establish the master and reviewer set
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.
- 12d ago First seen · 151 lines · 60 tokens per session scan A ff3949ca0a9d
collating-reviewer-feedback is a skill published in the GitHub repository LegalQuants/lq-skills (54 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,512 once invoked, about $0.0003 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-mcp
Use when creating or editing Word (.docx) documents — from scratch, from markdown, or from templates. Triggers: creating documents, converting markdown to docx, reviewing contracts, marking up reports, adding revision comments, validating document structure, removing watermarks, auditing OOXML integrity, bulk text…
docx-draft
Convert Word documents to structured markdown for LLM-assisted editing, then convert back to Word with preserved formatting. Make sure to use this whenever the user wants to work on, revise, draft, fill in, or collaboratively edit a .docx and then produce a final .docx again. Prefer this over markitdown or…
document-generation
Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. Use when someone needs a deliverable rather than an answer — a change record to attach to a CR, an audit workbook for a compliance reviewer, a…
hermesoffice-documents
Produce and edit Word documents in HermesOffice Docs — block editing, tracked changes, reports, and the templates/docs library (meeting notes, business plan, PRD, decision memo, and more). Load for any request that creates or restructures a document.
hermesoffice
Core conventions for working inside the HermesOffice suite (Docs, Sheets, Slides, PDF) — session continuity, tool selection, and the save-and-reload contract. Load whenever a request originates from a HermesOffice AI panel or targets an office document on this machine.
office-artifacts
Manage Office files, formats and versions; use Writer, Calc or Impress for content.