agentleFS
hfadhlullahhfadhlullah/kaizen/skills/kaizen-help/SKILL.md

kaizen-help

Skill6 starsChanged 45 days agoMITView on GitHub

Quick-reference card for the kaizen commands, with pointers to the full docs. One-shot display, not a persistent mode. Trigger: /kaizen-help, "kaizen help", "what kaizen commands", "kaizen cheat sheet".

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read these from the kaizen skill folder, which sits beside this one:

    line 65
  2. Very specific:

    Every setting and its default: config.default.yml

    line 68

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Kaizen Help

Print the content of this card into your reply. The user cannot see this file — it loads into your context only, so summarizing it or saying "see above" shows them nothing. Output the tables themselves.

One-shot: do NOT change kaizen's active mode, write to state.json, or persist anything.

Commands

InvocationAction
/kaizen <request>Start a new run in the configured mode (default: approve)
/kaizen plan <request>Start a run and stop after the plan (plan-only)
/kaizen auto <request>Start a run in auto mode: every stage back to back, no approval stops
/kaizen lite <request>Run the stages in this session — cheap, reviewer has seen the work (unless review.executor: subagent)
/kaizen full <request>Dispatch each stage as its own cold agent
/kaizen explore <request>Question the idea and research uncertainties before Plan, for one run
/kaizen skip-explore [request]Skip Explore for this run; keep the saved toggle
/kaizen runResume the current run and execute the approved plan
/kaizen review [target]Review-only: audit existing code, no plan, no implementation
/kaizen statusList every run grouped waiting-on-you / in flight / done / abandoned, plus open backlog count
kaizen done <id> [--user-approved]Finish a run; refused while the review gate waits on the user, --user-approved after a clear yes in chat
kaizen preflight <id>Before a push or merge: is the run behind its base, is CI failed or running, does another open PR, branch or run change the same files. Exit 0 clean, 2 stopped (ask the user; kaizen worktree land <id> --checked only after a go-ahead)
kaizen model [planner|builder|reviewer]The model to pass on that stage subagent's Agent call, from subagents.<stage> then subagents.model; inherit means pass none
kaizen state <id> key=value ...(1.69.0+) Set a run's stage, awaiting or iteration in state.json; refuses words no board knows (done goes through kaizen done)
kaizen stats [<id>] [--json](1.69.0+) Fix-round and CANNOT VERIFY rates, stage times, tokens for one run
kaizen related <path> ...(1.69.0+) Earlier runs that changed these files
/kaizen backlogPrint open backlog items across all runs, grouped by source run, rescued items last under Orphaned
/kaizen gatherRead request sources kaizen cannot read by itself; their requests land in the icebox, nothing starts
/kaizen discoverGroup what is in the icebox and promote the tasks you pick; nothing starts
kaizen icebox add [--file <f>] [--kind client|finding|people] [--collection <c> | --client <name>] [--tag <t>]"Put this in the icebox": a note, link or file, text from the file or stdin (never a shell word); a link's title is read
kaizen icebox edit|kind|tag|collection|snooze|unsnooze <ids> ..., kaizen icebox collectionsReword an item, set its kind, tags or collection, hide it until 1d/1w/1m/a date; list or add boards
/kaizen docs [lint]Write or refresh the project's docs vault in the notebook, which agents read first; lint only reports what is stale, broken or uncovered
kaizen automation list|add|run <id>|pause <id>|resume <id>|rm <id>|runs <id>Schedules that start an unattended auto-mode run in this project (hourly, daily, weekdays, weekly or cron; optional precheck). Fires only while a board runs
kaizen worker init|start <wid>|status|config|merge|set <run> on|offOrchestration (off by default): split a run into workers, each in its own board terminal and folder. kaizen worker report is for the workers themselves
/kaizen concept [number] <brief>Make product concepts as clickable prototypes and get one approved before any build
/kaizen roadmap [next [name] | run [name]]List roadmaps, start or resume the next phase, or run the remaining phases; a project too big for one run, of any kind
/kaizen approveApprove whatever the current run is waiting on
/kaizen reject <reason>Reject it; the reason decides revise (back to planner) vs kill (abandon)
/kaizen abortMark the current run abandoned
/kaizen configShow this project's settings and change them, one picker per setting
/kaizen initSet up this project folder: .kaizen/ with the spec*.md files, config, and — in a git repo — the gitignore entry
/kaizen installInstall the workflow itself globally or per-project
kaizen preview <localhost url | image>Show a change in the board (page → Browser tab, screenshot → Preview tab), not a new browser window
kaizen search "<query>" [--recent h|d|w|m|y] [--read] [--limit N]Web search through Firecrawl with your own key (Settings → Integrations → Research); exit 2 when no key is set
kaizen scrape <url>One web page as markdown, through the same Firecrawl key
kaizen send <file>... [--to <name | address>]Send files to a phone or computer through LocalSend; they accept on the device. --default <name | address> saves where files go (over Tailscale, the phone's address); --devices lists what is nearby. --whatsapp [--to <chat name | self>] [--text "caption"] sends through the WhatsApp linked in Settings → Phone instead (to yourself when --to is left out)
kaizen recall [--track t] [--tags a,b] [--query "<words>"]Lessons from other projects that match (global knowledge, ~/.kaizen/knowledge/)
kaizen remember --track t --tags a,b --applies "<where>" --run <id> "<lesson>"Save a lesson that holds beyond this project; the reviewer calls it

/kaizen with no argument: status if a run is in progress, else ask what to build.

More

Read these from the kaizen skill folder, which sits beside this one:

  • Modes, approvals, fix loop, state layout: SKILL.md
  • Every setting and its default: config.default.yml
  • Settings you can pick from: settings.md
  • Full walkthrough: README.md
  • Stage contract: spec.md
  • Porting to other tools: adapters.md

kaizen settings opens every setting in a terminal.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.