session
claudeWork session management — issue-driven and freeform doors sharing an explore-then-plan spine, with multi-agent orchestration and a wrap-up skill that reviews, sweeps issues, and ships
5 skills
Per-session inbox of questions (block on the user, drive a deterministic 'input needed' flag in hooks, statusline and notifications) and decisions (defaults the agent already took, reviewed later), with skills to view, answer and confirm them.
Plugin inbox from marketplace agent-toolkit in St0nefish/agent-toolkit. Commands read from the repo's manifest — today.
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.
answerWalk through the parked questions with the user in chat and record each answer.
confirmConfirm the decisions made on a default. With no arguments, accept all open decisions; with arguments, apply the user's notes or exclusions.
decisionsShow the decisions the agent made on a default and the user has not yet reviewed.
followupsRead-only checklist of the followups logged this session plus a live sweep of loose ends (uncommitted or unpushed work, open PR or worktree, pending questions and decisions).
park-questionUse when you are genuinely blocked on the user (a guess would be unsafe, or information is missing): park the question in the session inbox instead of writing an 'input needed' banner or asking mid-stream.
questionsShow the parked questions awaiting the user's answer in this session.
record-decisionUse when you proceed on a default for a key choice the user may want a say in (approach, architecture, naming, scope, assumptions): record it as a decision for later review instead of stopping to ask.
record-followupUse when you notice work worth doing before the session wraps up but not now (out of scope, deferred, docs or tests not done, a bug or issue to file): log it as a followup in the session inbox so it survives /compact and /clear.
respondHandle everything open in the inbox: answer parked questions first, then review recorded decisions.
showShow everything open in this session's inbox: parked questions, recorded decisions and logged followups.
triageInteractive one-by-one pass over the inbox: answer each parked question, then approve or change each recorded decision, using AskUserQuestion.
bash ${CLAUDE_PLUGIN_ROOT}/scripts/inbox-hook.sh
bash ${CLAUDE_PLUGIN_ROOT}/scripts/inbox-hook.sh
bash ${CLAUDE_PLUGIN_ROOT}/scripts/inbox-hook.sh
Work session management — issue-driven and freeform doors sharing an explore-then-plan spine, with multi-agent orchestration and a wrap-up skill that reviews, sweeps issues, and ships
5 skills
Recipe authoring, meal planning, grocery cart building, and dinner lookup against a knowledge-base-backed household profile. Reads preferences, dietary restrictions, pantry inventory, and store product vocabulary from a KB MCP server rather than embedding them.
4 skills
Status line for Claude Code built as a mod: user, project, git, model, context, usage, extra credits and cost, drawn under the prompt with colours that follow your terminal theme
3 skills · hooks
IDE-grade code intelligence for agents — Serena (LSP symbol nav/refactor) and ast-grep (AST search/rewrite) with usage cheatsheets, setup helpers, and a context-isolated explorer agent
2 skills · 1 agent
Auto-rename Claude Code sessions and terminal tab titles from git context (<repo>:<branch>), with a per-worktree override and /title-set + /title-clear slash commands. Skips emit when there's no useful name to attach.
2 skills · hooks
Java/JVM tooling — Maven Central intelligence, class search/decompilation (MCP via Docker), plus jar-explore for raw JAR content inspection
3 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.