Claude Code mod
lean-workflow
Token-efficient, self-improving Claude Code workflow: usage dashboard and guards, model rungs, read-only scout and independent reviewer agents, a code map, orient and gate scripts, size warnings, a habit coach with /coach, live limit bars and a tier that follows the weekly limit, modes (focus, triage, review, budget, release), guards and a morning briefing for unattended runs, an end-of-session retro, a per-item rung ledger and a weekly upgrade-scan.
Install
/plugin marketplace add Braydenh563/lean-workflow
/plugin install lean-workflow@lean-workflowMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: runs processes, writes files, drives Claude, reads prompt attachments, reads mod state, persists state, draws
- Sees
- mcp__lean-workflow__view calls, every prompt, subagent spawns, Read calls, Agent calls, TaskCreate calls, TaskUpdate calls, every tool call, every skill
- Draws in
Pane- Hooks
session.startcommand.runtool.callprompt.submitagent.spawnturn.completeprompt.composeplugin.registerskill.promptsession.endui.render
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- Braydenh563/lean-workflow
- Folder
.- Marketplace
lean-workflow- Author
- Braydenh563
- License
- MIT
- Last updated
- 18 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is lean-workflow?
Token-efficient, self-improving Claude Code workflow: usage dashboard and guards, model rungs, read-only scout and independent reviewer agents, a code map, orient and gate scripts, size warnings, a habit coach with /coach, live limit bars and a tier that follows the weekly limit, modes (focus, triage, review, budget, release), guards and a morning briefing for unattended runs, an end-of-session retro, a per-item rung ledger and a weekly upgrade-scan. It is a mod for Claude Code, from Braydenh563/lean-workflow on GitHub.
What can the lean-workflow mod access?
Its widest reach is "writes or runs" (runs processes, writes files, drives Claude, reads prompt attachments, reads mod state, persists state, draws). It sees mcp__lean-workflow__view calls, every prompt, subagent spawns, Read calls, Agent calls, TaskCreate calls, TaskUpdate calls, every tool call, every skill. It draws in Pane. Like any mod, it runs with your permissions.
How do I install lean-workflow?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add Braydenh563/lean-workflow and then /plugin install lean-workflow@lean-workflow.
Is lean-workflow popular?
Braydenh563/lean-workflow has 1 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 18 October 2026.
More context & usage mods
latex-render
1chang-07/cc-latex
Draws display LaTeX ($$...$$ or \[...\]) in assistant replies as typeset images (tectonic + kitty graphics)
leitstand
1fbrogno/claude-mods
Leitstand: Live-Dashboard für alle Claude-Code-Sitzungen: Titel statt Kürzel, leere Sitzungen gebündelt, kontoweite Limits, Crew-Übersicht je Sitzung mit gemessenen Token-Zahlen, Kosten und Cache-Trefferquote; Subagents als animierte Pixel-Männchen.
last-call
1Sunkanxx/Mods
Stops work at a clean point before the 5-hour (or 7-day) usage limit, keeps the prompt cache warm while waiting, and continues the work after the reset.
leo-mods
1quango2304/leo_claude_mod
Leo's Claude Code mods: usage bars, limits, cost, prompt cache countdown, active time and running agents
jojo-sbr-token-usage
1dodofk/jojo-sbr-token-usage
Context window usage as one line above the prompt, told as a Steel Ball Run race: Gyro's five lessons and a horse running to the finish flag.
limits
1justmorenoise/claude-code-limits
Usage band for Claude Code: context, 5h/7d limits and prompt cache as step-colored bars; keepwarm for the cache; handoff to a clean conversation after review; auto-compaction and auto-resume after a usage limit.
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.