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 lawve-ai/awesome-legal-skills --skill legal-diagram-sam-zhaigit clone --depth 1 https://github.com/lawve-ai/awesome-legal-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/lawve-ai/awesome-legal-skills/legal-diagram-sam-zhai)<a href="https://agentmods.dev/skills/lawve-ai/awesome-legal-skills/legal-diagram-sam-zhai"><img src="https://agentmods.dev/badge/skills/lawve-ai/awesome-legal-skills/legal-diagram-sam-zhai/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/lawve-ai/awesome-legal-skills/legal-diagram-sam-zhai"><img src="https://agentmods.dev/badge/skills/lawve-ai/awesome-legal-skills/legal-diagram-sam-zhai.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 | $0.00113 | $0.02282 |
| Opus 5.5 | $0.00045 | $0.00913 |
| Sonnet 5.5 | $0.00023 | $0.00456 |
| Haiku 4.5 | $0.00011 | $0.00228 |
Grade A, and why
legal-diagram 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 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.
- assets/html_template.html 56 KB
- constraints.txt 308 B
- LICENSE.txt 1.0 KB
- PORTABILITY.md 4.8 KB
- README.md 31 KB
- references/extraction-schema.md 4.6 KB
- requirements.txt 177 B
- scripts/check_setup.py 1.6 KB runs code
- scripts/diagram_selector.py 34 KB runs code
- scripts/eval_pass2.py 2.8 KB runs code
- scripts/extract_entities.py 5.3 KB runs code
- scripts/extraction/__init__.py 388 B runs code
- scripts/extraction/context.py 3.5 KB runs code
- scripts/extraction/domain.py 11 KB runs code
- scripts/extraction/domain/__init__.py 1.7 KB runs code
- scripts/extraction/domain/compliance.py 610 B runs code
- scripts/extraction/domain/core.py 5.2 KB runs code
- scripts/extraction/domain/corporate.py 431 B runs code
- scripts/extraction/domain/litigation.py 759 B runs code
- scripts/extraction/domain/result.py 4.9 KB runs code
- scripts/extraction/engine.py 1.2 KB runs code
- scripts/extraction/evaluation.py 19 KB runs code
- scripts/extraction/handoff.py 8.4 KB runs code
- scripts/extraction/harvesters/__init__.py 71 B runs code
- scripts/extraction/harvesters/_patterns.py 2.2 KB runs code
- scripts/extraction/harvesters/base.py 13 KB runs code
- scripts/extraction/harvesters/citations.py 28 KB runs code
- scripts/extraction/harvesters/conditions.py 720 B runs code
- scripts/extraction/harvesters/consent.py 2.4 KB runs code
- scripts/extraction/harvesters/controls.py 5.9 KB runs code
- scripts/extraction/harvesters/deadlines.py 8.2 KB runs code
- scripts/extraction/harvesters/documents.py 2.2 KB runs code
- scripts/extraction/harvesters/entities.py 7.8 KB runs code
- scripts/extraction/harvesters/events.py 7.2 KB runs code
- scripts/extraction/harvesters/notices.py 1.2 KB runs code
- scripts/extraction/harvesters/obligations.py 39 KB runs code
- scripts/extraction/harvesters/ownership.py 1.4 KB runs code
- scripts/extraction/harvesters/parties.py 14 KB runs code
- scripts/extraction/harvesters/party_mentions.py 6.3 KB runs code
- scripts/extraction/harvesters/payments.py 4.0 KB runs code
- scripts/extraction/harvesters/remedies.py 821 B runs code
- scripts/extraction/harvesters/reps.py 792 B runs code
- scripts/extraction/harvesters/tables.py 5.6 KB runs code
- scripts/extraction/helpers/__init__.py 1.2 KB runs code
- scripts/extraction/helpers/dates.py 1.4 KB runs code
- scripts/extraction/helpers/money.py 2.0 KB runs code
- scripts/extraction/helpers/scoring.py 1.2 KB runs code
- scripts/extraction/helpers/subjects.py 2.5 KB runs code
- scripts/extraction/language.py 4.6 KB runs code
- scripts/extraction/lexicon.py 3.3 KB runs code
- scripts/extraction/lexicon/__init__.py 5.9 KB runs code
- scripts/extraction/lexicon/base.py 6.6 KB runs code
- scripts/extraction/lexicon/en.py 19 KB runs code
- scripts/extraction/lexicon/fr.py 23 KB runs code
- scripts/extraction/manifest.py 6.1 KB runs code
- scripts/extraction/materialize.py 10 KB runs code
- scripts/extraction/patching.py 22 KB runs code
- scripts/extraction/resolver.py 12 KB runs code
- scripts/extraction/schema.py 1.7 KB runs code
- scripts/extraction/utils.py 14 KB runs code
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 · 112 lines · 113 tokens per session scan A cde698ebf3b7
legal-diagram is a skill published in the GitHub repository lawve-ai/awesome-legal-skills (903 stars, last pushed 8d ago), with no licence file. It adds 113 tokens to every session and 2,282 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 2026-09-03.
Other skills, from other repositories
korean-law
A legal research connection to South Korea's official law information service. It can retrieve statutes, court decisions, administrative rules, local ordinances, treaties, and legal interpretations, then check cited provisions against the source.
investment-and-shareholder-agreement-reviewer
Reviews venture and private-investment documents — term sheets, letters of intent, share subscription agreements, shareholders' agreements, investment agreements, joint-venture agreements, constitutional rights packages, and side letters — from one identified party's position (founder, investor, majority, minority…
arbitration-pleading-drafter
Drafts the merits pleadings in arbitration — statement of claim, statement of defence, counterclaim, and reply to counterclaim — with jurisdiction and admissibility objections, material facts, contractual and legal breaches, causation, quantum, and relief all tied to the evidentiary record. Use when a claimant needs…
clause-comparator
Compares the same clause or provision across draft rounds, precedents, public agreements or a portfolio and reports what differs in wording and effect. Use for version-change requests and external clause benchmarking, including "what changed between drafts", "compare their indemnity with ours", "compare liability caps…
learn-law-with-rohas
Acts as an interactive legal tutor for learning a law, legal subject, doctrine, judgment, procedure, or legal concept. Builds a learning path around the user's topic and level, teaches concepts step by step, uses examples and hypotheticals, asks questions and quizzes, explains mistakes, adapts difficulty, revises weak…
compensation-quantifier
Builds a compensation or damages claim head by head, using only the figures actually supplied, showing the arithmetic and flagging any head that is claimed without a supporting figure. Use this whenever a user wants a claim quantified rather than assessed on the merits — including phrasings like "work out what we can…