Project housekeeping for agentic engineering at five levels, Minimal to Immaculate, within a session, repo, or machine scope: quest and lore sync, safe git landing and pruning with containment proofs, workspace, runtime and Claude Code harness cleanup, and a verified disposition for every in-scope item, through a fingerprinted plan/apply engine with safety classes and undo.
Plugin housekeeping-skills from marketplace opum in opum-ai/opum-marketplace. Commands read from the repo's manifest — 4 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
loreAuthor, retrieve, and maintain OKF documentation with the lore CLI, including explicit multi-repository workspaces. Use whenever reading, writing, linking, moving, querying, or checking docs, so Story/Task coupling, managed blocks, provenance, and cross-links stay coherent. Run `lore instructions` f
questDrive this repo's task tracker with the quest CLI instead of editing backlog/tracker state directly. Use whenever creating, listing, viewing, editing, completing, or archiving tasks, drafts, milestones, or decisions in a Quest-initialized workspace. Run `quest instructions --list` for the workflow g
git-hygieneKeep git and GitHub clean the safe way - stage and commit in logical units, push, open and merge PRs, promote dev to main, and prune merged or gone branches (local and remote), worktrees, stashes, and stale refs without ever deleting unlanded work. Use this skill whenever the user asks to commit, pu
harness-hygieneKeep the Claude Code harness itself clean - old sessions and transcripts (including projects whose folders no longer exist), auto-memory and CLAUDE.md bloat, stale or superseded memories, the plugin cache and unused or context-heavy plugins, duplicate skills, hooks, one-off or overly broad permissio
runtime-cleanStop and remove the runtime leftovers of agentic work - dev servers and background processes a session started, orphaned node/bun/python processes still holding ports, this project's Docker containers, images, networks and volumes, dangling images and build cache - scoped by evidence (compose projec
session-syncReconcile the tracker and the docs with what this session actually did - progress notes, acceptance criteria checked only with evidence, tasks closed the right way, follow-up tasks for discovered work, lore docs updated and gated, and two-way spec drift resolved. Native to quest (tasks) and lore (do
tidyProject housekeeping after agentic engineering work, at a chosen level - Minimal (save a recoverable stopping point), Light (put away what you just used), Standard (the routine checklist, the default), Deep (the places routine housekeeping misses), or Immaculate (deep, plus verify every in-scope ite
workspace-cleanSafely clear files an agentic workflow leaves behind - agent junk (*.bak, *_v2.*, scratch scripts, debug logs, *_SUMMARY.md), temp dirs leaked by test runs into $TMPDIR, build outputs and dependency dirs (node_modules, dist, .venv, __pycache__, target), repo caches, and old Claude Code session scrat
/housekeeping-skills:cleanProject housekeeping at a level and scope - /clean minimal | light | standard | deep | immaculate [session|repo|machine] [audit]
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/capture.py"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/capture.py"
Explain and diagram architectures, processes, decisions, data and plans: Mermaid in Markdown, pitched to the reader's level, drawn from real Quest and lore records, and checked for syntax, legibility, accessibility and truth.
8 skills
Sustainable test suites for agentic engineering: a test constitution with rigor profiles (R1 Minimal to R5 High-Assurance), lean test planning, mutation-kill-matrix audits, certified test-suite reduction with probation, CI gates, and provable-coverage claims.
8 skills
Formal verification for real codebases: find concurrency, data-flow, state-management, and graph bugs with TLA+ and Lean 4, reproduce and fix them, simplify code with proofs, and publish results as Artifact reports.
6 skills
Three Claude Code output styles, Beginner, Intermediate and Advanced, that report in clear, jargon-free language built on ASD-STE100 Simplified Technical English. Every update answers what was done, whether it worked and what you do next; decisions come as two options with a recommendation. Only the communication changes, not the engineering.
3 skills
Drive the quest CLI: file, plan, record and complete tracker work in a Quest workspace. Federated: pinned to the quest-cli release tag so the skill cannot drift from the CLI it describes.
2 skills
Drive the lore CLI: author, retrieve, and maintain OKF documentation bundles, including explicit multi-repository workspaces. Federated: this entry pins the lore-cli release tag, so the skill is cut from the same tag as the CLI it describes and cannot drift from it.
1 skill
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.