word-choice

word-choice is a skill for Claude Code from ishwarjha/legalant. It costs 45 tokens per session (478 once invoked), scanned A, original, MIT.

A checklist for reviewing or drafting contracts, which are legal agreements between parties. It focuses on who can sign, what each party promises, payment, ending the agreement, risks, approvals, unclear wording, conditions, and taxes.

In plain words
What is it for?
Use it to check contract drafts, compare redlined versions, identify changed obligations, and review payment, termination, liability, approval, and tax provisions.
Why use it?
It helps reviewers notice common legal and business terms that can be missed when reading a contract line by line. It also treats changes to obligation words such as SHALL, WILL, MAY, and MUST as important.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the legalant plugin — 4 skills, 16 commands, 18 agents shipped together

Good fit Use it to check contract drafts, compare redlined versions, identify changed obligations, and review payment, termination, liability, approval, and tax provisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ishwarjha/legalant/word-choice
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 ishwarjha/legalant --skill word-choice
Clone the repo
git clone --depth 1 https://github.com/ishwarjha/legalant

Made for: Claude Code.

Or install legalant, the plugin that ships this one along with the rest of its 4 skills, 16 commands, 18 agents.

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 word-choice

README.md
[![agentmods](https://agentmods.dev/badge/skills/ishwarjha/legalant/word-choice/github.svg)](https://agentmods.dev/skills/ishwarjha/legalant/word-choice)
Your own site
<a href="https://agentmods.dev/skills/ishwarjha/legalant/word-choice"><img src="https://agentmods.dev/badge/skills/ishwarjha/legalant/word-choice/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 word-choice

Your own site · 80×15
<a href="https://agentmods.dev/skills/ishwarjha/legalant/word-choice"><img src="https://agentmods.dev/badge/skills/ishwarjha/legalant/word-choice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 478 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 $0.00045 $0.00478
Opus 5 $0.00023 $0.00239
Sonnet 5 $0.00009 $0.00096
Haiku 4.5 $0.00005 $0.00048

Measured 12d ago against content hash 3efc8fc44f44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

word-choice 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.

legalant/skills/word-choice/SKILL.md · 49 lines

What it actually says

Word Choice — Modal Verb Taxonomy

Apply to every contract review, redline analysis, and drafting task.


Verb Legal Force Usage Risk on Change
SHALL Mandatory obligation. Non-compliance = breach. Enforceable duties only. Downgrade to WILL = automatic Substantive flag
WILL Statement of intent / future action. Weaker enforceability. Future commitments, representations. Upgrade to SHALL = improves enforceability
WOULD Conditional or hypothetical. NEVER in operative clauses. Flag immediately — replace with SHALL or WILL
MAY Discretion or permission. Rights, options, permissions. Downgrade from SHALL = weakens obligation
COULD Possibility. NEVER in operative clauses. Flag immediately — ambiguous enforceability
MUST Equivalent to SHALL in modern drafting. Use SHALL for consistency in Indian contracts. Acceptable if consistent throughout

Golden Rule

Any change between these verbs across contract versions is automatically a Substantive change, regardless of context.

Flag every instance. State:

  1. The original verb
  2. The replacement verb
  3. The legal consequence of the change
  4. The recommended correction

Common Traps

  • "The Company will pay" — does "will" mean a promise or intention? Use SHALL if it's a duty.
  • "Either party may terminate" — discretionary; neither party has an obligation to terminate.
  • "The Board would consider" — hypothetical; creates no obligation. Replace with SHALL consider.
  • "Counterparty can request" — "can" implies ability, not right. Use MAY for permissions.

DPDP Act 2023 Note

Section 7 consent obligations: data principals SHALL be notified (mandatory). Use SHALL for all data processor obligations under the Act.

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. 12d ago First seen · 49 lines · 45 tokens per session scan A 3efc8fc44f44

Subscribe to this mod's changes

word-choice is a skill published in the GitHub repository ishwarjha/legalant (6 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 478 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 2026-08-31.