Skill Claude CodeCodex
Run pre-commit quality checks for a Maven/Java project — auto-format, validate Checkstyle and PMD, and run the tests. Use before creating a commit, and when the user says "run the pre-commit checks", "am I ready to commit", "check this before I commit", or "is the working tree clean".
Plugin Claude Code
Keep agent-written memory files from rotting: re-verifies pinned facts against the tree (version pins, sequence facts, vanished paths) and flags what has become wrong, checks MEMORY.md index drift both ways, and enforces the memory format contract at write time. Flags, never deletes — supersession is strike-through…
Skill Claude CodeCodex
Keep agent-written memory files from rotting. Audits /.claude/projects/ /memory/ for facts the tree now contradicts — stale version pins, passed sequence facts, vanished paths — plus MEMORY.md index drift, and enforces the memory format contract at write time. Use when the user says "audit my memory", "memory is…
Plugin Claude Code
Drop ideas on a canvas, connect them, and compile the map into an organized Markdown prompt. Offline and dependency-free: a self-contained page for capture, a deterministic compiler for the map -> prompt step, and JSON Canvas (.canvas) as the save format so a map can be reworked later or opened in Obsidian. A ✦…
Command
Compile a saved mind map into an organized prompt and act on it.
Command
List the saved mind maps in this repo.
Command
Open the mind-map canvas to sketch ideas, then compile them into a prompt.
Skill Claude CodeCodex
Think on a canvas, then compile the map into an organized prompt. Idea nodes connect freely and a deterministic compiler turns the whole map into structured Markdown; ✦ expands any node with claude -p running in the repo, so ideas stay grounded in the project. Maps save as JSON Canvas, so they are git-diffable and…
Plugin Claude Code
One visible channel for every long-running process — local sweeps, backgrounded commands, and work handed to external systems. The server that serves the live progress page IS the tracker: a tiny stdlib Python daemon holds live jobs in memory (auto-spawned by the first producer, single writer, no store locking)…
Skill Claude CodeCodex
One visible channel for every long-running process — local sweeps, backgrounded commands, and work handed to external systems (a CI run, a media-server queue, a long download). The server that serves the live progress page IS the tracker — a stdlib Python daemon holding live jobs in memory, auto-spawned by the first…
Plugin Claude Code
Analyzes each prompt you submit against a tiered ruleset of prompting best practices; nudges you toward better prompts (definition-of-done, scoped references, guardrails, verification steps) and quietly graduates rules you consistently follow.
Command
Analyze a specific prompt (or your last N prompts) against the full rule catalog and coach improvements.
Command
View or edit prompt-coach config — categorized dashboard, per-key describe/set/reset, diff, export.
Command
Launch the local prompt-coach web dashboard (stats, mastery, live config editor).
Command
Show prompt-coach help — commands, config options, and say-it phrases.
Command
Find a gold-standard prompt template from Anthropic's Claude Code Prompt Library for a task.
Command
Show current mastery — which rules mastered, which are in progress, which need reset. Enhanced analysis (v0.26+) flags untested masteries so you can spot rules that may be irrelevant to your patterns rather than truly internalized.
Command
File a privacy-safe bug report about a prompt the coach mistreated or missed.
Command
Show prompt-coach health metrics — fires, praises, corrections, mastery, active rules.
Skill Claude CodeCodex
A hook-driven coach that reads every prompt sent to Claude Code and rewrites it toward proven prompting habits — definition-of-done, scoped references, guardrails, verification. Rules graduate as they are demonstrated, so the coaching fades as the user improves. The hook runs on its own, but load this skill when the…
Plugin Claude Code
A self-evolving 'discover' crew: it composes a task-fit team of coverage roles for an information space, fans them out in parallel, dedups, and adversarially verifies their findings into one trustworthy, cited result. The discover counterpart to dev-crew (deliver) and brainstorm-panel (decide).
Skill Claude CodeCodex
The "discover" orchestrator on the shared role substrate — counterpart to dev-crew (deliver) and brainstorm-panel (decide). Composes a task-fit team of coverage roles, partitions the space into non-overlapping angles, fans them out as parallel agents under one output contract, then dedups and adversarially verifies…
Plugin Claude Code
Specialist review subagents for Java/Maven projects — code review, test running, and dependency/CVE auditing on lighter model tiers. No-write by construction: Write and Edit are withheld, so they read, build, and report without touching the working tree.
Agent
Audit dependencies for CVEs and outdated versions. Use for security checks or before releases.