agentleFS
kaynetikkaynetik/skills/legalizer/SKILL.md

legalizer

Skill1 starsChanged 8 months agoMITView on GitHub

Audits and rewrites public-facing content (website copy, docs, announcements, social posts, whitepapers) for Web3/crypto protocol projects to eliminate securities-risk language and enforce utility-token framing. Applies guardrails derived from the SEC/CFTC joint interpretive rule, Howey test analysis, and FinCEN non-custodial guidance. Use when reviewing or writing any externally published content about a token, staking, governance, fees, or protocol participation -- or when the user mentions legalizer, compliance review, token language, Howey, securities risk, public copy, or utility framing.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All copy must reflect the SEC/CFTC digital commodity test: value derives from the programmatic operation of a functional system, not from …

    line 14
  2. Distinctive:

    When reviewing any content, flag every instance of:

    line 18
  3. Distinctive:

    Write with the confidence of an engineering team, not a financial product:

    line 57
  4. Distinctive:

    Use active protocol language: "the contract verifies," "validators sign," "governance votes"

    line 60
  5. Distinctive:

    Avoid superlatives and marketing inflation ("revolutionary," "game-changing")

    line 61
  6. Distinctive:

    Use these terms freely:

    line 66
  7. Distinctive:

    Do not sanitize accurate technical descriptions:

    line 85

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Legalizer

Enforces legal guardrails on public-facing content for Web3 protocol projects. Goal: keep every published statement in the "utility" lane -- functional, operational, descriptive -- and scrub anything that could trigger a Howey analysis or SEC/CFTC securities classification.

Core Rule

Describe what the token does. Never describe what the token earns.

All copy must reflect the SEC/CFTC digital commodity test: value derives from the programmatic operation of a functional system, not from the managerial efforts of others or expectation of profit.

Audit Checklist

When reviewing any content, flag every instance of:

Hard Blocks (must rewrite, no exceptions)

PatternWhy
"earn," "yield," "return," "ROI," "APY," "APR," "passive income"Implies profit expectation (Howey prong 4)
"revenue," "profit," "earnings," "income" describing token holder outcomesSecurities language
"investment," "investor," "invest in"Direct investment framing
"fee capture," "value accrual," "revenue share," "fee revenue flows to"Implies economic benefit from others' efforts
"appreciation," "upside," "price target," "token value will"Forward-looking financial promise
"stake to earn," "staking rewards" (when framed as income)Passive income framing
Any specific price, price projection, or revenue estimateProhibited in all contexts
"get a share of," "profit from the protocol"Revenue distribution framing

Soft Flags (review context, often rewrite)

  • "rewards" -- acceptable only when clearly tied to computational work, not financial return
  • "incentives" -- acceptable for participation incentives, not financial incentives
  • "benefits" -- acceptable for governance/utility benefits, not financial benefits
  • "grow," "growth" -- acceptable for network growth, not token value growth

Approved Substitutions

Flagged phraseApproved replacement
"earn staking rewards""receive validator compensation for computational work"
"passive income from staking""validators are compensated for operating network infrastructure"
"revenue flows to token holders""fee parameters are set by governance"
"invest in the protocol""participate in network operations"
"token value appreciation""network participation and governance rights"
"profit from fees""service fees sustain network operations"
"stakers earn a share""validators receive token distributions for computational work"
"ROI on staking"(remove -- no acceptable substitute)
"get returns""participate in governance"
"fee capture mechanism""operational cost coverage model"

Tone Standard

Write with the confidence of an engineering team, not a financial product:

  • Describe mechanics, not outcomes
  • Use active protocol language: "the contract verifies," "validators sign," "governance votes"
  • Avoid superlatives and marketing inflation ("revolutionary," "game-changing")
  • Third-person factual preferred for docs; second-person action-oriented for UX copy ("you submit a proof," not "you'll earn")

Approved Vocabulary

Use these terms freely:

  • Network participation, computational work, validator operations
  • Governance rights, protocol parameter voting, on-chain governance
  • Service fee, operational cost, network sustainability
  • Token distribution, validator compensation, contributor allocation
  • Shielded transfer, privacy-preserving, ZK proof, non-custodial
  • Open-source protocol, permissionless, trustless

Rewrite Workflow

  1. Scan the full document for every Hard Block term (grep/search for the word list above)
  2. Flag each instance with the category: [HARD BLOCK] or [SOFT FLAG]
  3. Apply the approved substitution or rewrite the sentence to remove the concept entirely
  4. Re-read the rewritten passage -- if a reasonable reader could interpret it as a financial promise, rewrite again
  5. Confirm: no price projections, no yield figures, no income claims remain anywhere in the document

What to Preserve

Do not sanitize accurate technical descriptions:

  • ZK proof mechanics, circuit parameters, bridge architecture
  • Governance process descriptions (voting, quorum, timelock)
  • Token supply, distribution schedule, vesting (factual, not as investment pitch)
  • Validator requirements (stake size, hardware, uptime) -- these are operational facts
  • Fee amounts or rates expressed as operational parameters, not investor returns

Quick Reference: The Howey Test

A token is a security if it is: (1) an investment of money, (2) in a common enterprise, (3) with expectation of profits, (4) from the efforts of others.

Your copy must neutralize prongs 3 and 4 in every sentence. Describe utility, mechanics, and governance. Never describe profit expectation or reliance on the team's efforts to generate returns.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.