--- title: "house-rules" description: "Versioned engineering playbook for AI coding agents: skills for code review, over-engineering audits, prose voice, planning, and TDD discipline." canonical: https://agentpluginsdirectory.com/plugins/house-rules last-updated: 2026-09-22 --- # house-rules Versioned engineering playbook for AI coding agents: skills for code review, over-engineering audits, prose voice, planning, and TDD discipline. - Slug: house-rules - Publisher: Kevin Glynn - Repository: https://github.com/kevglynn/house-rules - Manifest: plugin.json - License: Apache-2.0 - Category (editorial): code-review - Skills: 17 (bead-authoring, brainstorming, council, graph-planning, graybeard-audit, graybeard-debt, graybeard-help, graybeard-review, packet-deepdive, packet, pragmatic-tdd, prose-voice, refinement, systematic-debugging, tier1-review, tier2-handoff, workspace-kickoff) - MCP servers: 0 - Stars: 0 - Repository created: 2026-07-16 - Repository last pushed: 2026-09-08 - Publisher type: User - Listing: https://agentpluginsdirectory.com/plugins/house-rules - Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json ## What house-rules does, in the publisher's words A versioned engineering playbook for AI coding agents, rules and checkers that make process knowledge checkable, not something you hope the model remembers. Works with Cursor and Claude Code today. Everything is plain markdown plus stdlib-only Python and bash, so nothing locks you to a tool. Paste this into any terminal. No clone, no plugin, no account: just curl and python3: - Rules: always-on law the agent reads every session (identity, deferrals, prose voice, subagent safety, the graybeard ladder). - Checkers: single-file stdlib CLIs (banned-token-scan, defer-lint, …) with stable exit codes you can run locally or in CI. Checkable, not silently "enforced" by the model. - Tell your agent "use house-rules." It runs the doctor and offers bootstrap, sync, or update with your consent. From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/kevglynn/house-rules/HEAD/README.md ## Skills - bead-authoring: Single-bead lifecycle playbook: authoring worked examples (bd create with description/ACs/non-goals), dedupe search, validation mechanics (bd lint / --dry-run), wisps, JIT verification on pickup, progress notes, self-review before close, close-reason format with examples, and the bd remember when/… - brainstorming: This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore approaches", ambiguous feature… - council: Convene a council of diverse AI voices to analyze a task from multiple perspectives using different models. Each voice operates as a full-capability generalPurpose subagent (reads, shell, MCPs) with its own analytical lens. Synthesizes perspectives rather than ranking them. Use when the user says "… - graph-planning: Planner playbook for multi-bead breakdowns: decomposition heuristics, atomic dependency-graph creation with bd create --graph, graph verification, and mid-flight epic management (stuck children, scope expansion, honest epic close). Trigger phrases: "plan this epic", "break down this initiative", "… - graybeard-audit: Whole-repo audit for over-engineering. Like graybeard-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from th… - graybeard-debt: Harvest every `defer:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals get tracked instead of rotting into "later means never". Use when the user says "graybeard debt", "/graybeard-debt", "what did we defer", "list the shortcuts", "debt ledger", or "what did we… - graybeard-help: Quick-reference index for the graybeard family: which skill or rule to use for over-engineering review, repo-wide audit, defer-ledger harvesting, or minimal-implementation mode. One-shot display, not a persistent mode. Trigger: "graybeard help", "use graybeard", "which graybeard skill", "how do I u… - graybeard-review: Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can w… - packet-deepdive: Validate a drafted gate/sprint packet with a four-lane deep-dive: accuracy-vs-repo, cold-read (the overlay's reader persona and access boundary), receipts verification (re-run every count/string/exit-code live), and navigability/structure, with a phase-2 convergence round between accuracy and cold… - packet: Author a gate/sprint review packet from a committed blueprint: gather the gate's bead evidence and receipts, populate the reader's-own-checklist status grid with a divergence strip, a capped FAQ, and exactly three linked receipts, carry the decision vocabulary into the reader's repo, then verify it… - pragmatic-tdd: Per-bead-type TDD playbooks: the operational procedure behind the pragmatic-tdd rule. Use when starting a bug/feature/refactor bead, when you need to write the failing test, or when proving red-then-green after the fact. Triggers on "pragmatic tdd", "starting a bug/feature/refactor bead", "write t… - prose-voice: Voice discipline for human-facing prose: pattern catalog, self-correction protocol, and worked examples for killing AI-sounding rhetorical tics. Load when writing positioning docs, pre-whitepapers, packets, deck copy, primers, emails, briefs, or any prose a human will read or forward. Trigger phra… - refinement - systematic-debugging - tier1-review - tier2-handoff - workspace-kickoff Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.