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-ai --skill comms-improvergit clone --depth 1 https://github.com/LegalQuants/lq-aiWrote 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-ai/comms-improver)<a href="https://agentmods.dev/skills/legalquants/lq-ai/comms-improver"><img src="https://agentmods.dev/badge/skills/legalquants/lq-ai/comms-improver/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-ai/comms-improver"><img src="https://agentmods.dev/badge/skills/legalquants/lq-ai/comms-improver.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 | $0.00121 | $0.03014 |
| Opus 5.5 | $0.00048 | $0.01206 |
| Sonnet 5.5 | $0.00024 | $0.00603 |
| Haiku 4.5 | $0.00012 | $0.00301 |
Grade A, and why
comms-improver 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comms Improver
Rewrite legal text in plain language for a specified non-legal audience. The output preserves meaning while changing form: shorter sentences, common words instead of jargon, active voice instead of passive, concrete examples instead of abstract formulations. The skill is transformation, not drafting from scratch.
This skill is for the everyday in-house counsel task of translating between legal precision and non-legal accessibility. Lawyers spend significant time rewriting their own work — or reviewing others' rewrites — for executive readouts, sales communications, customer disclosures, deal-team briefings, and engineering specs. The skill does this rewriting (or supports the user's rewriting) while flagging where translation involved interpretation.
When this skill applies
Apply when the user has legal-jargon-heavy text and wants it rewritten for a specified non-legal audience. Common inputs:
- Email drafts to non-legal business stakeholders.
- Contract clauses to be explained to a deal team or product team.
- Legal disclaimers to be rewritten for customer-facing surfaces.
- Memos to be summarized for executive readouts.
- Regulatory developments to be communicated to affected business functions.
- Compliance obligations to be translated for the operational owner.
Do not apply when:
- The user wants to draft text from scratch. Out of scope — the skill rewrites existing text. Drafting from scratch is a different shape (drafting skill candidate; deferred enhancement).
- The user wants to translate between languages (e.g., English to Spanish). Out of scope.
- The user wants legal review of someone else's plain-language rewrite. Out of scope; that's review, not rewriting. The user can paste both versions and ask whether the rewrite preserves meaning, but the skill is calibrated for the rewriting task.
- The text is already plain language and the user wants a different style. Out of scope; that's editing for style, not rewriting for accessibility.
- The user wants to "make this sound more legal" or "add legal weight." Out of scope — the skill goes from legal to plain, not the other direction. Adding legal precision to plain text is a different task with different risks (introducing meaning the original didn't carry).
What ships with it
12 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.
- acceptance/fixtures/disclaimer-for-customers.md 2.3 KB
- acceptance/fixtures/indemnity-for-sales.md 3.0 KB
- acceptance/fixtures/memo-for-exec.md 2.8 KB
- acceptance/snapshots/disclaimer-for-customers.golden.json 1.1 KB
- acceptance/snapshots/indemnity-for-sales.golden.json 1.1 KB
- acceptance/snapshots/memo-for-exec.golden.json 1007 B
- examples/example_customer_disclaimer.md 11 KB
- examples/example_executive_briefing.md 8.5 KB
- examples/example_sales_team.md 9.7 KB
- reference/audience_calibration.md 11 KB
- reference/legal_to_plain_patterns.md 11 KB
- test-plan.md 9.8 KB
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 First seen · 186 lines · 121 tokens per session scan A 9614f50b69eb
comms-improver is a skill published in the GitHub repository LegalQuants/lq-ai (156 stars, last pushed today), licensed Apache-2.0. It adds 121 tokens to every session and 3,014 once invoked, about $0.0005 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
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
terms-of-service
Draft terms of service and a companion privacy notice matched to the product's form and feature modules, not legal advice, delivered as a Word document.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
ai-risk-management
Apply the NIST AI Risk Management Framework (AI RMF 1.0) and adjacent guidance to AI / ML systems — model lifecycle governance, fairness and bias evaluation, robustness, transparency, accountability, third-party model risk, monitoring for drift, and AI incident response. Broader than prompt-injection (which is the…