agentleFS
Sign inStart free
IgorGanapolskyIgorGanapolsky/ThumbGate/.agents/skills/saas-moat-honesty-not-clone/SKILL.md

saas-moat-honesty-not-clone

Skill29 starsChanged 7 months agoMITView on GitHub

Audit ThumbGate against Rob Walling's 8 SaaS moats, enforce Ed25519 signed entitlements on learned models and exporters, and aggregate anonymized cross-customer gate signatures without leaking raw transcripts.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill when evaluating SaaS defensibility, entitlement boundaries (scripts/entitlement.js, scripts/license.js), seat-compression …

    line 8
  2. Very specific:

    No Closed-Source Theater (MOAT.md): Never claim ThumbGate-Core holds secret code when 212/216 scripts ship in npm pack thumbgate.

    line 12
  3. Very specific:

    Enforce Ed25519 Entitlements on Crown Jewels: Keep the 5 learned models (risk-scorer.js, bayes-optimal-gate.js, thompson-sampling.js, …

    line 13
  4. Very specific:

    Cross-Customer Signatures Without Raw Transcript Leakage: Use distillCrossCustomerSignature() and aggregateCrossCustomerLoop() to aggregate …

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

SaaS Moat & Seat-Compression Honesty (Walling 2026 FORMAT)

Use this skill when evaluating SaaS defensibility, entitlement boundaries (scripts/entitlement.js, scripts/license.js), seat-compression pricing, or cross-customer rule learning (scripts/saas-moat-honesty.js).

Non-Negotiable Rules

  1. No Closed-Source Theater (MOAT.md): Never claim ThumbGate-Core holds secret code when 212/216 scripts ship in npm pack thumbgate. Defensibility comes from Agency (PreToolUse <5ms interdiction), Operational Grit (7-CLI adapter matrix), System of Record (tamper-evident ledgers), and the Ed25519-gated Learning Loop.
  2. Enforce Ed25519 Entitlements on Crown Jewels: Keep the 5 learned models (risk-scorer.js, bayes-optimal-gate.js, thompson-sampling.js, agent-reward-model.js, intervention-policy.js) and 3 exporters (export-dpo-pairs.js, export-hf-dataset.js, export-databricks-bundle.js) gated behind scripts/entitlement.js. Forged tg_pro_... prefix keys must fail when THUMBGATE_ENFORCE_ENTITLEMENTS=1.
  3. Cross-Customer Signatures Without Raw Transcript Leakage: Use distillCrossCustomerSignature() and aggregateCrossCustomerLoop() to aggregate secret-redacted, path-normalized SHA-256 structural rule signatures across orgs (uniqueOrgs >= 2, occurrenceCount >= 3). Never exfiltrate raw transcripts or unredacted secrets.

Commands

npx thumbgate saas-moat-honesty --json
npx thumbgate saas-moat-honesty --map-only --json
node --test tests/saas-moat-honesty.test.js tests/license.test.js tests/entitlement.test.js

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.

Check your setup, free