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 local-first-legal-workspacegit 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/local-first-legal-workspace)<a href="https://agentmods.dev/skills/legalquants/lq-skills/local-first-legal-workspace"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/local-first-legal-workspace/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/local-first-legal-workspace"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/local-first-legal-workspace.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 | $0.00065 | $0.01381 |
| Opus 5 | $0.00032 | $0.00691 |
| Sonnet 5 | $0.00013 | $0.00276 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
local-first-legal-workspace 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
local-first-legal-workspace
When to Use
- A lawyer wants to use AI with confidential documents without adopting a hosted matter platform.
- A desktop or local web app stores legal documents and generated work product.
- The user needs to reason about BYOK model calls, local storage, workspace backups, or privacy boundaries.
- A workflow must explain exactly what leaves the machine.
This skill is a design and audit checklist. It is not a claim that local-first equals risk-free.
Audience and Work Shape
Audience: legal-technology counsel, privacy/security-aware lawyers, and legal engineers reviewing a legal AI workspace with technical input where needed.
Work shape: pattern-matched audit when evidence exists; accretive design review when the user is designing a workflow. Keep those paths separate in the output.
Legal Failure Modes
- Legal support, not legal advice: the skill maps data flows and uncertainty so a lawyer can assess risk; it does not certify privacy, security, privilege, or regulatory compliance.
- Privilege/confidentiality: model calls, document conversion, logs, and external lookups can affect privilege/work-product treatment. Include privilege/work-product implications in the disclosure note when legal matter data is involved.
- Accountability: the responsible lawyer, DPO, security lead, or system owner decides whether the workspace is acceptable for a matter or client.
Access Modes
This skill works in three modes:
- Code/runtime evidence mode - inspect repository code, configuration, dependencies, logs, network observations, or runtime behavior.
- User-supplied architecture mode - use diagrams, README files, screenshots, settings exports, or descriptions supplied by the user.
- No-evidence mode - produce an audit plan and questions only. Do not assert what stays local or what leaves the machine.
If code, runtime evidence, or provider documentation is unavailable, mark claims unknown or not_observed_not_excluded. Do not treat a product's privacy statement as verified architecture.
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 · 155 lines · 65 tokens per session scan A dad3cc5f96dd
local-first-legal-workspace is a skill published in the GitHub repository LegalQuants/lq-skills (54 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,381 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
Privacy Advisor
Privacy Advisor delivers defensive, authorized, auditable security analysis with explicit scope boundaries and risk handling.
hatch-pet
Create, repair, validate, preview, and package Codex-compatible animated pet spritesheets from character art, screenshots, generated images, or visual references. Use when a user wants to hatch a Codex pet, create a custom animated pet, or build a built-in pet asset with an 8x9 atlas, transparent unused cells…
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
github-dashboard
GitHub repository analytics dashboard — stars, forks, contributors, issues, pull requests, recent activity, and top contributors. Use when the brief asks for a GitHub repo dashboard, open-source growth report, repository health page, or GitHub analytics view.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…