house-tell-guard
Skill4 starsChanged 31 days agoMITView on GitHub
Enforce the physical Gate 0 commit-sheet, break agent internal house tells, and mandate category reflex inversion before any code generation.
In this repository47 other files it gives its agents.
- AGENTS.mdAGENTS.md
- anti-slop-engineeringSkill
- anti-slop-engineeringSkill
- api-ergonomics-and-contract-governorSkill
- apple-craft-and-frame-budgetSkill
- apple-craft-and-interaction-physicsSkill
- asset-provenance-guardSkill
- backprop-guardSkill
- chaos-and-degradation-choreographerSkill
- chromatic-drift-guardSkill
- cognitive-load-and-attention-governorSkill
- comment-budget-guardSkill
- context-window-and-token-economics-architectSkill
- cryptographic-agility-and-secret-lifecycle-gateSkill
- decision-guardSkill
- demock-guardSkill
- design-system-drift-guardSkill
- deterministic-simulation-and-property-testingSkill
- distributed-consensus-and-concurrency-gateSkill
- finops-and-unit-economics-governorSkill
- future-scale-gateSkill
- grumpy-senior-staff-engineerSkill
- honeypot-trap-guardSkill
- install-anti-slopSkill
- llm-eval-and-prompt-injection-fortressSkill
- mandela-guardSkill
- mechanical-sympathy-and-perf-gateSkill
- mechanical-sympathy-profilerSkill
- motion-runtime-guardSkill
- observability-and-slo-architectSkill
- observability-and-slo-gateSkill
- paranoid-principal-architectSkill
- pr-boundary-guardSkill
- privacy-and-data-lineage-gateSkill
- re0-handoff-guardSkill
- reduction-guardSkill
- repo-memory-and-invariant-stewardSkill
- root-fix-gateSkill
- safe-evolution-and-rollout-choreographerSkill
- scientific-fault-isolationSkill
- styleseed-guardSkill
- supply-chain-and-sbom-sentinelSkill
- tagore-guardSkill
- type-level-and-ast-slop-gateSkill
- ui-and-copy-disciplineSkill
- verification-oracle-architectSkill
- zero-downtime-migration-gateSkill
The file
Files
Agent House-Tell & Triple-Reflex Inversion Guard
Require physical commit-sheet contracts on disk before code generation, eliminating category clichés and agent self-referential design habits.
Why This Skill Is Needed & Target State
Slop is not ugliness; it is predictability. Generative models operate at three altitudes of reflex:
- First-Order Reflex: What generic AI does for the category (e.g. AI tool = dark mode + neon blue glow + terminal mono).
- Second-Order Reflex: What an AI trying to avoid the first order does (e.g. editorial serif on off-white "anti-SaaS" cliché).
- Third-Order Reflex (The House Tells): The subconscious habits of the agent or framework itself across unrelated projects (near-black background, mono corner labels, glowing borders, identical 3-card bento grids, decorative comment banners).
The target state is a physical, signed Gate 0 Pre-Commit Sheet (.anti-slop/commit-sheet.json or design/COMMIT-SHEET.md) that contractually breaks at least two house tells and commits non-default architectural decisions before code generation begins.
Invariant Rules
- Gate 0 Physical Deliverable: Zero code modification is permitted before
.anti-slop/commit-sheet.jsonordesign/COMMIT-SHEET.mdexists and passes validation. - The Seven Commitments: The commit-sheet must provide non-generic, substantive answers for:
- Peak / Signature Element (one sentence).
- Color Strategy & Numeric Lightness ($L_{\text{target}}$).
- Typographic Contrast Axis (rejecting Inter/Space Grotesk defaults).
- Grid / Structure Break (concrete asymmetry or overlap).
- Motion Budget ($\le 3$ scroll pattern families).
- Category Reflex Check (1st order, 2nd order, and argued departure).
- House Tells Broken: Minimum 2 habits of the agent itself contractually barred with explicit replacements.
- Anti-Truism Filter: Generic marketing statements ("clean, modern look", "user-friendly design", "beautiful animations throughout") are rejected with exit code 2.
CLI Usage
# Initialize a starter commit sheet template
bunx anti-slop-engineering house-tell --init-template
# Validate active commit sheet
bunx anti-slop-engineering house-tell --file .anti-slop/commit-sheet.json
# Validate markdown commit sheet with JSON output
bunx anti-slop-engineering house-tell --file design/COMMIT-SHEET.md --json --strictDoes 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
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.

