claude

working-method

Skills for how Claude works on a task: hard multi-step tasks, context docs, surviving a usage limit, and git worktrees

2 on GitHubby lbzepoqov0.1.1MITupdated 2 days ago
/

Plugin working-method from marketplace lbzepoqo in lbzepoqo/claude-plugins. Commands read from the repo's manifest — yesterday.

What it installs

Skills (4)

  • context-docs

    How to write and audit CLAUDE.md, AGENTS.md and other context docs (map, not mirror), and what belongs in CLAUDE.md versus a skill. Use before adding to or editing any CLAUDE.md or project context doc, and when auditing one.

  • hard-task-playbook

    Working method for hard, multi-step tasks - how to decompose them, how to verify your own output, and how to decide the next move. Load at the start of any task with real unknowns (subtle bugs, multi-file changes, unfamiliar platforms, anything where a wrong-but-plausible answer is expensive).

  • usage-limit-recovery

    How to leave work safe to interrupt (plan file, wip commit, memory) and how to resume it in a new session, with checkpoint markers in plan files. Use when writing or updating a plan file in ~/.claude/plans, when a usage limit may hit, when making a wip commit, or when resuming interrupted work.

  • worktrees

    When and where to create a git worktree, and when to remove it. Use before creating a worktree, before `claude --worktree`, or when a checkout must stay on one branch while another branch is worked on (a deploy or mirror branch, several branches in flight, two sessions in one repo).

View source on GitHub

More from lbzepoqo/claude-plugins

All 10 plugins →

compact-timing

claude

Compacts the conversation at task boundaries instead of at a fixed token count: the model marks the session busy or at a boundary, and the plugin compacts at the end of a turn when the mark and the context size allow it

2

grounded

claude

Output style: answer first, keep every figure, do the work you can do, and say what was checked

2

memory-hints

claude

Points Claude to the saved auto-memory notes that match each prompt you type, so a note is read before the work it applies to instead of sitting unread behind its index line

2

plugin-updates

claude

Tells you when installed plugins or copied skills are behind upstream, without updating them: a status line, one toast per news, and a /plugin-updates list of the missing commits

2

quality-nudge

claude

Reminds Claude to run code-review after a code commit that no review saw: from 30 changed lines, or any change to guard code; adds /simplify from 300 lines

2

secret-guard

claude

Keeps secrets out of the conversation: hides keys before Claude or the transcript sees them, and blocks credential files and commands that print secrets. Fork of arasovic/claude-code-mods

2

Maintain working-method?

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.

claude & codex plugins10 plugins