Command Claude Code
Find and fix bugs that break OpenLore's first-run experience by dogfooding the real install flow on a clean repo (the method that found the orient-CLI, --no-embed, watcher-EMFILE, and install-index bugs).
Instructions file CodexOpenCode
Instructions for clay-good/OpenLore, covering openlore: llm agent instructions, agent role, core principles, workflow and step 1: codebase survey.
Instructions file
Instructions for clay-good/OpenLore, covering openlore mcp tools — when to use them, agent skills, issue tracker, triage labels and domain docs.
Agent
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
Agent
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
Agent
The skills speak in terms of five canonical triage roles. This file maps those roles to the label strings that actually exist in this repo's issue tracker.
Agent
The architecture document MUST reflect the reality of the code, not just the desired target state. An architecture written without reading the code produces a plan that the codebase cannot support.
Agent
When riskcontext is absent from a story, this override enforces a full structural gate at implementation time as a safety net.
Skill Claude CodeCodex
Run a full static OpenLore analysis and summarize architecture, call graph, refactoring issues, and duplicate code. Use when asked to analyze, map, or assess a codebase without LLM inference.
Skill Claude CodeCodex
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
Skill Claude CodeCodex
Debug with OpenLore structural context, an explicit root-cause hypothesis, and RED/GREEN verification. Use when a bug, failure, or regression needs diagnosis and repair.
Skill Claude CodeCodex
Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.
Skill Claude CodeCodex
Author a new OpenSpec domain specification from deterministic OpenLore MCP evidence. Use when asked to reverse-engineer, generate, or document a specification for existing code.
Skill Claude CodeCodex
Implement a brownfield story with OpenLore orientation, risk checks, spec validation, tests, and drift detection. Use when asked to implement or continue a story in an existing codebase.
Skill Claude CodeCodex
Identify a high-priority refactoring target, assess its blast radius, and write .openlore/refactor-plan.md without changing code. Use when asked to plan or prioritize a refactor.
Skill Claude CodeCodex
Review code changes using OpenLore risk, call, coverage, and cluster evidence without editing code. Use when asked for a change review, pre-PR safety check, or merge recommendation.
Skill Claude CodeCodex
Write and run real tests for a function or spec scenario after reading implementation and contract evidence. Use when asked to add, improve, or repair tests without stubs or placeholders.
Command
Post-implementation spec drift check — verify the implementation matches existing OpenSpec specifications.
Command
Pre-flight structural risk check — orient + analyzeimpact before implementation. Gates on riskScore ≥ 70.
Skill Claude CodeCodex
Retrieve relevant functions, callers, spec sections, and insertion points from OpenLore before reading source files. Use when starting work that needs structural orientation in an existing codebase.
Skill Claude CodeCodex
Reconcile one existing OpenSpec specification from deterministic OpenLore MCP observations. Use when a spec may be incomplete, stale, partially covered, or orphaned from current code.
Cursor rule
OpenLore orient() workflow.
Instructions file CodexOpenCode
Instructions for clay-good/roughlogic.com, covering agents.md, what this repo is, use the calculators as an agent (the fast path), the repo map and how to add or change a calculator.
Instructions file
Instructions for clay-good/roughlogic.com: This project uses OpenLore for persistent architectural memory.