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 ishwarjha/legalant --skill word-choicegit clone --depth 1 https://github.com/ishwarjha/legalantWrote 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/ishwarjha/legalant/word-choice)<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.
<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>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 | $0.00045 | $0.00478 |
| Opus 5 | $0.00023 | $0.00239 |
| Sonnet 5 | $0.00009 | $0.00096 |
| Haiku 4.5 | $0.00005 | $0.00048 |
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.
What it actually says
Word Choice — Modal Verb Taxonomy
Apply to every contract review, redline analysis, and drafting task.
Modal Verb Hierarchy
| 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:
- The original verb
- The replacement verb
- The legal consequence of the change
- 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.
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 · 49 lines · 45 tokens per session scan A 3efc8fc44f44
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.
Other skills, from other repositories
nda-review
A first-pass checker for incoming non-disclosure agreements (NDAs), which are contracts that restrict sharing confidential information, under Russian law. It sorts them into green, yellow, or red categories.
vendor-agreement-review
A contract-review skill for checking incoming vendor agreements against a team playbook under Russian law. A vendor agreement sets the terms for buying services, work, or supplies from another company.
dsar-response
A guided response to a personal-data subject’s request to view, correct, delete, or restrict use of their data, or withdraw consent. It checks identity, finds the data across systems, considers exceptions, and drafts the reply.
amendment-history
A contract-change history that compares the original agreement with every later addendum, or follows how one specific clause changed over time.
contract-review
A paragraph-by-paragraph review of commercial contracts under Russian law, with legal citations, counterparty checks, court-case research, risk levels, and proposed wording changes.
nda-draft
A tool for drafting one-way or mutual non-disclosure agreements under Russian law. An NDA is a contract that restricts how confidential information may be shared or used.