Skill Claude CodeCodex
Calibrate this machine's Claude Code setup. Runs a read-only Opus orchestrator that chains a planner, an evaluator (audits every feature — CLAUDE.md, rules, settings, skills, subagents, hooks, MCP, plugins — and how they interact, against the shipped doc-set), and a calibrator that applies the approved improvements…
Skill Claude CodeCodex
Read-only audit — runs the calibration planner-init and evaluator-baseline phases, prints the per-feature findings, then stops. No improvement plan, no approval gate, no edits. The same first half of /calibrate. Use this as a periodic health check or a CI gate when you only want to know "what's wrong" without applying…
Skill Claude CodeCodex
Compare the current Claude Code setup against the previous calibration run's baseline. Spawns only the evaluator (pass 2) — no planner, no calibrator, no edits. Useful between calibration runs (you manually edited a few files; what now shows resolved vs new?) and as a "did my changes hold up?" check after merging a…
Skill Claude CodeCodex
Fast structural health check for a Claude Code setup. Detects broken config — JSON that doesn't parse, hook scripts that are missing or non-executable, subagent/skill files with malformed frontmatter, MCP servers whose command can't be found, and .gitignore that's missing .claude/calibration/. Prints a terse triage…
Skill Claude CodeCodex
Evaluate the BEHAVIOUR of a multi-step workflow, not static config: does the chain deliver intent, and are its agent→agent / agent→skill handoffs sound? Drives a named workflow over a case set of golden fixtures (each /{input/,expected.md}), diffs what it finds against the oracle, and scores node recall/precision…
Skill Claude CodeCodex
First-time setup guide for claude-calibration and Claude Code config in general. Detects what config the project already has (CLAUDE.md, .claude/, settings.json, hooks, agents, skills, .mcp.json), names the minimal viable additions for this project's stack, and bridges into /claude-calibration:calibration-doctor…
Skill Claude CodeCodex
Track whether calibration is actually improving your Claude Code setup across iterations. Takes a deterministic snapshot of the current config (a structural floor from calibration-doctor plus signature-keyed lint over all nine features), anchors a baseline to the last PR merged onto main, keeps a local gitignored…
Skill Claude CodeCodex
Discovery-friendly dispatcher above /calibrate. With no args, prints a menu of every calibration flow — the three /calibrate built-in modes (tighten / harden / cost), the two standalone convenience flows (audit, diff), and the per-feature shortcuts (skills / subagents / claude-md / rules / settings / hooks / mcp /…
odere-pro/claude-oop-excellence
Plugin Claude Code
Use when auditing, reviewing, or refactoring a codebase for object-oriented design quality in any language. A single read-only front door, /audit, runs two analysis tracks in parallel — RISK (issues) and PATTERN (existing-pattern scan + pattern-fit suggestions) — and merges them into one unified report; every layer…
odere-pro/claude-oop-excellence
Hook Claude Code
Runs before the agent uses a tool for Write, Edit, MultiEdit and Write tool calls, executing block-secrets.sh and block-large-files.sh via bash (2 commands). From odere-pro/claude-oop-excellence.
odere-pro/claude-oop-excellence
Instructions file
Claude Code instructions for odere-pro/claude-oop-excellence, covering claude-oop-excellence — plugin development, what ships, source layout, agents and house rules.
odere-pro/claude-oop-excellence
Agent
Use to validate one glossary entity OR a whole family of them (code smells, antipatterns, vulnerabilities, supply-chain risks) against a target scope in a single pass. The orchestrator injects one entity record — or a family batch of records — plus scope and file manifest; this worker checks each entity's…
odere-pro/claude-oop-excellence
Agent
Use to fix a single glossary entity (one code smell, antipattern, vulnerability, or supply-chain risk) in a given scope. The orchestrator injects one entity record and a scope; this worker detects instances by the entity's signs, applies the smallest corrective refactor guided by its correctivepatterns, then verifies…
odere-pro/claude-oop-excellence
Agent
The plugin's central orchestrator across both audit tracks. Delegate when a project or component needs analysis or action over its code quality and design. Reads the glossary, resolves the caller's selection through the track → aspect → family/category/entity layers, then fans out one generic worker per in-scope…
odere-pro/claude-oop-excellence
Agent
Use to implement a single design pattern into a target scope with a safe parallel-change sequence, then verify with the project's own detected tests. The orchestrator injects one design-pattern record plus scope and an optional plan-only mode; this worker confirms the resolved issue is present, introduces the pattern…
odere-pro/claude-oop-excellence
Agent
Use to analyze design patterns in a target scope — detect which are already implemented (scan), judge where one would help (fit), or both in a single read. The orchestrator injects one design-pattern record — or a family batch of records — plus a lens (scan | fit | both), scope, and file manifest; this worker reads…
odere-pro/claude-oop-excellence
Agent
Use to evaluate whether a design pattern would help (FIT / opportunity) in a target scope — where the pattern is only partially present and worth formalizing, not where it already exists. Accepts one design-pattern record or a family batch plus scope and file manifest; assesses candidacy — where the pattern's signs…
odere-pro/claude-oop-excellence
Command
Use to fix risk findings via the fix verb (improve → oop-orchestrator fix mode) — the gated FIX action the /audit report's Recommended Actions hands off to. Resolves an entity selection against the glossary and applies the smallest corrective refactor per in-scope entity, OOP first, verified with the project's own…
odere-pro/claude-oop-excellence
Command
Use to apply design patterns via the implement verb (pattern-implement → oop-orchestrator pattern-implement mode) — the gated IMPLEMENT front door the /audit report's Recommended Actions hands off to. Resolves a pattern selection against the glossary and applies each via the safe 4-step refactoring sequence with…
odere-pro/claude-oop-excellence
Skill Claude CodeCodex
Use before releases, after large PRs, or during onboarding to run a single read-only analysis of a codebase's quality, risk, and design. The one analysis front door. Reads the glossary to resolve a selector that zooms across three layers — track, aspect, family/category/entity — then delegates to the oop-orchestrator…
odere-pro/claude-oop-excellence
Skill Claude CodeCodex
Use to look up the canonical name, category, family, principle, signs, and severity of any code smell, antipattern, vulnerability, supply-chain risk, or design pattern this plugin recognizes. Read-only reference: resolve an entity by id, list every entity in a family or category, or check which corrective patterns fix…
odere-pro/claude-oop-excellence
Skill Claude CodeCodex
Use after /audit flags problem areas, or directly on a smell/antipattern/family, to apply the smallest corrective refactor and verify it with the project's own detected commands. The FIX action reached from the audit report's Recommended Actions handoff (/fix-risks ). Resolves the selection against the glossary and…
odere-pro/claude-oop-excellence
Skill Claude CodeCodex
Use when someone is new to claude-oop-excellence and asks how to use it, where to start, what /audit does, or which command to run next — a read-only orientation to the plugin. Explains the mental model (one read-only front door, /audit; three layers; two tracks — RISK and PATTERN) and the analyze → act flow that…
odere-pro/claude-oop-excellence
Skill Claude CodeCodex
Use after /audit pattern-fit surfaces an opportunity, or directly on a design-pattern id, to implement that pattern into a target scope with a safe parallel-change sequence and verify it with the project's own detected commands. Resolves the pattern against the glossary and delegates to the oop-orchestrator in…