demand-draft

demand-draft is a skill for Claude Code from uk-agents/uk-legal-plugins. It costs 85 tokens per session (5,198 once invoked), scanned A, original, Apache-2.0.

A legal drafting tool for a Letter Before Action or Letter of Claim, a formal notice sent before starting a court claim.

In plain words
What is it for?
Use it to turn completed case information into a draft demand letter, a Word document, and a checklist for actions after sending.
Why use it?
It checks important risks such as privilege, admissions, waiver, and the intended negotiation position before a demand is written.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Part of the litigation-legal-uk plugin — 16 skills, 1 agent shipped together

Good fit Use it to turn completed case information into a draft demand letter, a Word document, and a checklist for actions after sending.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/uk-agents/uk-legal-plugins/demand-draft
Install

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.

Any agent
npx skills add uk-agents/uk-legal-plugins --skill demand-draft
Clone the repo
git clone --depth 1 https://github.com/uk-agents/uk-legal-plugins

Made for: Claude Code.

Or install litigation-legal-uk, the plugin that ships this one along with the rest of its 16 skills, 1 agent.

Wrote 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.

agentmods badge for demand-draft

README.md
[![agentmods](https://agentmods.dev/badge/skills/uk-agents/uk-legal-plugins/demand-draft/github.svg)](https://agentmods.dev/skills/uk-agents/uk-legal-plugins/demand-draft)
Your own site
<a href="https://agentmods.dev/skills/uk-agents/uk-legal-plugins/demand-draft"><img src="https://agentmods.dev/badge/skills/uk-agents/uk-legal-plugins/demand-draft/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.

agentmods 80×15 button for demand-draft

Your own site · 80×15
<a href="https://agentmods.dev/skills/uk-agents/uk-legal-plugins/demand-draft"><img src="https://agentmods.dev/badge/skills/uk-agents/uk-legal-plugins/demand-draft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.05198
Opus 5 $0.00043 $0.02599
Sonnet 5 $0.00017 $0.01040
Haiku 4.5 $0.00009 $0.00520

Measured 5d ago against content hash 8803c692796f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

demand-draft 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 5d 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.

litigation-legal-uk/skills/demand-draft/SKILL.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/demand-draft

  1. Load ~/.claude/plugins/config/uk-legal-plugins/litigation-legal-uk/demand-letters/[slug]/intake.md. Refuse if missing or strategic block empty (for material demands).
  2. Load ~/.claude/plugins/config/uk-legal-plugins/litigation-legal-uk/CLAUDE.md → Letter Before Action practice, house style, seed-doc table.
  3. Follow the workflow and reference below.
  4. Run the pre-draft gate: privilege filter, admission risk, without-prejudice posture, waiver scan, tone, factual accuracy. Do not proceed until each is engaged.
  5. Template select: seed doc if provided in ~/.claude/plugins/config/uk-legal-plugins/litigation-legal-uk/CLAUDE.md; else soft template for the demand type.
  6. Draft in-chat for review. Iterate until user approves.
  7. Write ~/.claude/plugins/config/uk-legal-plugins/litigation-legal-uk/demand-letters/[slug]/draft-v[N].docx using the docx skill.
  8. Write ~/.claude/plugins/config/uk-legal-plugins/litigation-legal-uk/demand-letters/[slug]/checklist.md (post-send checklist).
  9. Assess materiality per heuristic; offer to create a matter. If yes: hand off to matter-intake with pre-populated fields.

Demand Draft

Purpose

Take a completed intake and produce a sendable draft. Most of the value is in refusing to draft until privilege, waiver, admission, and settlement-communication posture have been consciously addressed — the failure mode is a letter that waives LPP or constitutes an admission because no one paused to check.

Record fidelity — quotes and pinpoints

Demand letters are advocacy, and every quoted line from a contract, an email, or a prior communication becomes an assertion the counterparty will test.

Verbatim quotes must be verbatim. Never put quotation marks around words attributed to the counterparty, their solicitors, a witness, or any document unless you have the exact passage in front of you. When you want to characterise without the exact words:

  • Paraphrase without quotation marks, with a placeholder: "Your [date] email stated X [verify exact quote — email cite pending]."
  • Never fill the gap. A misquoted contract provision in a demand letter is the fastest way to lose credibility with the counterparty's solicitors on the first round.
  • Every [verify exact quote] must be flagged in the reviewer note before the letter leaves.

Read the full file on GitHub · 340 lines

Changes

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.

  1. 5d ago First seen · 340 lines · 85 tokens per session scan A 8803c692796f

Subscribe to this mod's changes

demand-draft is a skill published in the GitHub repository uk-agents/uk-legal-plugins (9 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 85 tokens to every session and 5,198 once invoked, about $0.0004 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 2026-09-03.