workbench-core
claudeCore infrastructure: persistent agent identity, session lifecycle hooks, operational memory, and meta skills. Customizable agent name and memory path.
15 skills · 2 agents · 1 MCP server · hooks
BuJo ritual system: daily, weekly, monthly, and yearly interactive reflections in Apple Notes. Scheduled rituals with on-demand slash commands.
Plugin workbench-bujo from marketplace claude-workbench in mike-bronner/claude-workbench. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
/workbench-bujo:bujo-captureCapture a single experientially-significant moment to today's BuJo daily log. Fast — no ritual, no prompts, just logs it.
/workbench-bujo:bujo-daily-ritualRun the daily BuJo ritual ad-hoc — orchestrator plans first, then the universal protocol runs for the daily tier only.
/workbench-bujo:bujo-habit-addAdd a habit to the current month's tracker. Walks an interactive interview (name → quantity? → time → cadence) via AskUserQuestion, then adds the column to the monthly note's habit-tracker table.
/workbench-bujo:bujo-habit-doneMark a habit as done for today. Updates the cell in the current monthly note's habit tracker. For quantitative habits, asks "how much?" before dispatching.
/workbench-bujo:bujo-habit-listList the habits on this month's tracker with cadence, time, and current progress (completion rate, streak) — rendered as an inline HTML habit dashboard, with a text table as fallback. Read-only — doesn't modify the note.
/workbench-bujo:bujo-habit-removeRemove a habit column from the current month's tracker. The previous month's tracker retains the column (historical). Asks for confirmation before removing.
/workbench-bujo:bujo-monthly-ritualRun the monthly BuJo ritual ad-hoc — orchestrator plans first, then the universal protocol runs for the monthly tier only.
/workbench-bujo:bujo-setupConfigure the BuJo plugin — timezone, note names, ritual schedule. Deploys a single unified scheduled task that runs /bujo each morning; the orchestrator decides which tiers fire. Re-run after a plugin update.
/workbench-bujo:bujo-weekly-ritualRun the weekly BuJo ritual ad-hoc — orchestrator plans first, then the universal protocol runs for the weekly tier only.
/workbench-bujo:bujo-yearly-ritualRun the yearly BuJo ritual ad-hoc — orchestrator plans first, then the universal protocol runs for the yearly tier only.
/workbench-bujo:bujoUnified BuJo ritual entry point. Dispatches the bujo-orchestrator to plan today's rituals, surfaces any anomalies to Mike, then runs each ritual skill in order.
bujo-orchestratorDetermines which BuJo rituals should run today and reports any anomalies (missed rituals, skipped streaks, out-of-date summary notes). Read-only inspector — never mutates notes, never runs the rituals themselves. Dispatched by the /bujo router skill or scheduled tasks.
scriberuns: bash ${CLAUDE_PLUGIN_ROOT}/scribe/bin/launcher.sh serve
bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-warmup.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-warmup.sh"
Core infrastructure: persistent agent identity, session lifecycle hooks, operational memory, and meta skills. Customizable agent name and memory path.
15 skills · 2 agents · 1 MCP server · hooks
Active write-back, human-approved, tax-aware YNAB budget review and categorisation assistant.
3 skills · 13 commands · 1 agent · 1 MCP server · hooks
The Index-driven dev pipeline: Inspector Lestrade (triage), Dr. Watson (dev work), and Sherlock Holmes (code review) as subagents. Interactive or unattended dispatch.
4 skills · 1 command · 10 agents · hooks
Turns AI development work in GitHub repos into reviewed, reproducible FreshBooks time entries.
2 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
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.