wm
claudecodexWork lifecycle management v2 — phased workflows (research, plan, implement) with agents, commands, and hooks.
18 skills · 34 commands · 20 agents · hooks · LSP
Split the working tree of every nearby git repo into logical commits at hunk granularity. A sonnet subagent proposes the split into an editable file, the operator answers each block, a second subagent builds the commits in a throwaway worktree and cherry-picks them back.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin smart-commit in popoffvg/dotfiles. Commands read from the repo's manifest — 4 days ago.
smart-commitWhat makes a logical commit when splitting a working tree at hunk granularity, and the contract of the proposal file the operator answers. Read by the smart-commit agent in both phases — the propose phase writes against this format, the apply phase reads answers back out of it.
/smart-commit:smart-commitAnalyze the diff across nearby repos, propose a logical commit split, let the operator answer each block, then commit
smart-commitSplits the uncommitted work of every nearby git repo into logical commits at hunk granularity. Runs in one of two phases named in the prompt — propose writes an editable proposal file and touches no git state, apply reads the answered proposal and builds the commits in a throwaway worktree before ch
Work lifecycle management v2 — phased workflows (research, plan, implement) with agents, commands, and hooks.
18 skills · 34 commands · 20 agents · hooks · LSP
Authoring aids for the Claude Code harness — skill shapes (workflow, loop, instruction, router), golden words that stand in for a rule set, pruning an existing skill or doc corpus into the house style, repo bootstrap (README, CLAUDE.md, deploy and adr skills, settings), and agent-work metrics from a per-turn ledger (re-ask ratio and causes, prompts to done, pasted blocks that should be a skill).
8 skills · 2 agents · hooks
Review comments on lines of any file, kept outside the file. Zed writes them through the line-comment language server; /line-comment:act reads the store and does the work, /line-comment:write places comments, /line-comment:unresolved reports what is still open, /line-comment:prune throws comments away, /line-comment:distill turns the habits act saved into review rules.
5 commands
Per-session prompt stack: push/pop/list/drop prompts across a session.
4 commands
Scores every Claude Code session for the lessons it holds and proposes where each one belongs in the harness: a watermarked background scan kicked by the SessionStart hook, one haiku call per dirty session, then a suggestion pass over the existing skill inventory. Browsable in the self-improve TUI. High scorers are archived for the capture-lesson skill to turn into skills and the dream skill to consolidate.
3 skills · hooks
Push, pop and list prompt drafts in files under ~/.claude/prompt-stack, from a key-opened menu
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.