Legal AI Model Router Stephane Boghossian

What it does

When your agent uses it

• Tasks that involve Model routing and gateways
• Tasks that involve Contract review
• Tasks that involve Legal research

Example prompts

• “s Legal Agent Benchmark, the Atticus Project”
• “Use the legal-ai-model-router-stephane-boghossian skill to route any legal task to the right LLM, like OpenRouter but for legal work and grounded in…”
• “/legal-ai-model-router-stephane-boghossian”

Requirements

• Pre-approved tools (allowed-tools): AskUserQuestion, Read

Workflow steps

3 steps, taken from the step headings in SKILL.md.

1. 1Classify the vertical
2. 2The four intake axes (shared by every vertical)
3. 3Output (uniform across the bundle)

What it can do on your machine

Read from SKILL.md and the folder at commit 045f738. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • AskUserQuestion
  • Read

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Legal AI Model Router Stephane Boghossian loads about 1.5k tokens when it runs. Until then it costs about 217 tokens; SKILL.md has 540 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~217

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from lawve-ai/awesome-legal-skills at commit 045f738, republished under its AGPL-3.0-or-later licence (© lawve-ai). 540 words, ~1,493 tokens.

name

legal-ai-model-router-stephane-boghossian

description

Routes any legal task to the right LLM, like OpenRouter but for legal work and grounded in benchmarks instead of brand loyalty. Built from mid-2026 legal evals (legalbenchmarks.ai, Vals AI × Stanford LegalBench across 124 models, Harvey's Legal Agent Benchmark, the Atticus Project's CUAD/MAUD/ACORD) plus translation evidence (WMT25, SwiLTra-Bench, ArabLegalEval). Covers five verticals: contract drafting, info extraction, legal research, contract review, and legal translation (including Arabic/MENA). Each asks up to four questions (cost, speed, accuracy/stakes, privacy/jurisdiction/language), then returns a primary model, a fallback, what to avoid, and what a human must verify. Core principle: capability is not controllability, so every route ends with a verification step. Not legal advice; a lawyer owns the output.

allowed-tools

AskUserQuestion, Read

version

0.1.0

triggers

which model or LLM should I use for this legal task, route this legal work to the right model, best AI model for a legal task, pick a model for me

license

AGPL-3.0-or-later

metadata.author

Stephane Boghossian

metadata.license

agpl-3.0

metadata.version

2026-07-14

TASK:       <vertical(s) detected>
PRIMARY:    <model> — <one line tying the pick to the axes + benchmark>
FALLBACK:   <model> — <when to switch>
ESCALATE IF: <trigger> → <stronger model / human>
AVOID:      <model> — <why, for THIS task>
CONFIDENCE: low | med | high
VERIFY:     <what a human must check> (+ live re-check link if stakes are High)

© lawve-ai, AGPL-3.0-or-later. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files in skills/legal-ai-model-router-stephane-boghossian of lawve-ai/awesome-legal-skills.

• SKILL.md
• README.md
• data/scorecard-2026-07.md
• skills

Open the folder on GitHubat commit 045f738