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

deeppattern-discipline-honesty-not-clone

Skill29 starsChanged 7 months agoMITView on GitHub

DeepPattern Agent Quality Gates + Decision Engine are neighbors, not a ThumbGate clone. Steal layer-check (same-layer substitutes only) and evidence-closeout (six required items before "done") onto existing rails. Never install AQG/DE/dp-install or unpark a cross-vendor audit SKU. Slash: /deeppattern-discipline-honesty-not-clone.

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Before saying done/fixed/shipped: Evidence/Closeout heading + six items.

    line 63
  2. Distinctive:

    Do not vendor AQG/DE.

    line 64

≈ “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

DeepPattern discipline honesty — compare, do not clone

Goal

Fail-closed comparative analysis and completion claims for whom: ThumbGate FORMAT steals and Completion Claim Contract — so L4 API gateways / hosted multi-model panels cannot be treated as PreToolUse substitutes, and "done" cannot pass without six evidence items.

Constraints

NEVERALWAYS
Install AQG, Decision Engine, dp-installnpx thumbgate deeppattern-discipline-honesty --json
Treat OpenRouter / LiteLLM / token pools as ThumbGate competitorsTag L1–L8; same job-to-be-done only
Claim done without evidence heading + six items--closeout=path.md --strict
Unpark LLM adjudicator / cross-vendor panel SKUDeterministic local gates; hosted panel stays external

HARD fail closed. REFUSE SKU clones.

Reference

Examples (show, don't tell)

Weak: "LiteLLM commoditizes ThumbGate because both route models."

Gold:

$ npx thumbgate deeppattern-discipline-honesty --json --map-only
ok: true
$ npx thumbgate deeppattern-discipline-honesty --json \
    --claim='LiteLLM replaces ThumbGate PreToolUse'
ok: false  # cross_layer_substitute

Procedures

npx thumbgate deeppattern-discipline-honesty --json --map-only
npx thumbgate deeppattern-discipline-honesty --json --claim='DE replaces ThumbGate'
npx thumbgate deeppattern-discipline-honesty --json --closeout=pr-body.md --strict
npm run test:deeppattern-discipline-honesty
  1. Tag subject + every cited product L1–L8 before competitive claims.
  2. Drop cross-layer substitutes; keep dependency language when honest.
  3. Before saying done/fixed/shipped: Evidence/Closeout heading + six items.
  4. Do not vendor AQG/DE.

Rubric

  • --map-only → ok=true
  • substitute claim naming L4/L2/L5 vs ThumbGate → cross_layer_substitute
  • --clone-deeppattern / dp-install → fail
  • closeout missing heading or item / placeholder → fail
  • doctor tests PASS
  • evidence: --json in the same turn

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