safe-review

safe-review is a skill for Claude Code from skala-io/legal-skills. It costs 84 tokens per session (3,372 once invoked), scanned A, original, Apache-2.0.

A review and advisory skill for YC SAFE agreements, legal documents that let a startup receive investment in exchange for future equity under specified terms. It also explains how SAFEs work and can draft a standard YC SAFE.

In plain words
What is it for?
Use it to review or compare an uploaded SAFE, ask how SAFEs work, or draft a standard YC SAFE for a US Delaware corporation.
Why use it?
It helps founders and lawyers spot differences from standard YC forms and understand the agreement's investment terms before seeking legal advice.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the legal-skills plugin — 11 skills shipped together

Good fit Use it to review or compare an uploaded SAFE, ask how SAFEs work, or draft a standard YC SAFE for a US Delaware corporation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skala-io/legal-skills/safe-review
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 skala-io/legal-skills --skill safe-review
Clone the repo
git clone --depth 1 https://github.com/skala-io/legal-skills

Made for: Claude Code.

Or install legal-skills, the plugin that ships this one along with the rest of its 11 skills.

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 safe-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/skala-io/legal-skills/safe-review/github.svg)](https://agentmods.dev/skills/skala-io/legal-skills/safe-review)
Your own site
<a href="https://agentmods.dev/skills/skala-io/legal-skills/safe-review"><img src="https://agentmods.dev/badge/skills/skala-io/legal-skills/safe-review/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 safe-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/skala-io/legal-skills/safe-review"><img src="https://agentmods.dev/badge/skills/skala-io/legal-skills/safe-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,372 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 $0.00084 $0.03372
Opus 5 $0.00042 $0.01686
Sonnet 5 $0.00017 $0.00674
Haiku 4.5 $0.00008 $0.00337

Measured 13d ago against content hash c5201e4b0544, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

safe-review 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 13d 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.

skills/safe-review/SKILL.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

First published on Skala Legal Skills

This skill is provided for informational and educational purposes only and does not constitute legal advice. The analysis and information provided should not be relied upon as a substitute for consultation with a qualified attorney. No attorney-client relationship is created by using this skill. Laws and regulations vary by jurisdiction and change over time. Always consult with a licensed attorney in your jurisdiction for advice on specific legal matters. The creators and publishers of this skill disclaim any liability for actions taken or not taken based on the information provided.


YC SAFE Review Skill

Review and advise on Y Combinator SAFE (Simple Agreement for Future Equity) agreements.

Note: The standard YC SAFE is designed for US Delaware C-corporations only. SAFE-style instruments for other jurisdictions (Singapore, Cayman, BVI, Panama) exist but have jurisdiction-specific modifications. Always confirm the company's incorporation jurisdiction first.

Entry Points

This skill handles three scenarios:

  1. Template Review - User uploads a SAFE for comparison against canonical YC templates
  2. Legal Questions - User asks how SAFEs work
  3. Drafting Request - User wants to generate a standard YC SAFE

Workflow

1. Template Review

When user uploads a SAFE agreement:

  1. Identify which YC SAFE variant it most closely matches:

    • templates/Postmoney Safe - Valuation Cap Only.docx (most common)
    • templates/Postmoney Safe - Discount Only.docx
    • templates/Postmoney Safe - MFN Only.docx
  2. CRITICAL: Perform exhaustive clause-by-clause comparison against the canonical template:

    • Read both documents completely
    • Compare every defined term
    • Compare every section and subsection
    • Flag ANY deviation - even single word changes
    • Note additions, deletions, and modifications
  3. Report findings:

    • List ALL differences found (or confirm exact match)
    • Explain legal significance of each difference
    • Assess whether changes favor company or investor
    • Flag any unusual or potentially problematic terms

Read the full file on GitHub · 347 lines

Files

What ships with it

5 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.

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. 13d ago First seen · 347 lines · 84 tokens per session scan A c5201e4b0544

Subscribe to this mod's changes

safe-review is a skill published in the GitHub repository skala-io/legal-skills (48 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 3,372 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 2026-08-30.

Related

Other skills, from other repositories

expense-review-policy

Review invoices and contracts against accounts-payable policy before human approval.

openai/openai-cookbook · 17 tokens

kyc-doc-parse

Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.

anthropics/financial-services · 49 tokens

audit-support

Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.

anthropics/knowledge-work-plugins · 45 tokens

fiscaliste

Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…

romainsimon/paperasse · 302 tokens

regulatory-analysis

Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.

open-gitagent/opengap · 59 tokens

subcontractor-payment-tracker

Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 25 tokens