The craft bar leaves this plugin and becomes craft-bar, installed from the same marketplace with /plugin install craft-bar@craft. The Claude plugin directory accepts mods only from Verified organizations, so craft ships no mod and the directory can list it. Updating craft alone removes the bar until craft-bar is installed; /craft:bar is now /craft-bar:bar.
My Claude Code workflow.
The skills, agents and instructions I use as a professional Software Engineer. It's called Craft, and it's a plugin you can install.
View the Craft source on GitHub juanwmedia/craft$claude plugin install craft --marketplace juanwmedia/craft
What never changes.
-
01
You decide what the agent cannot infer: the domain, the architecture, the structure of what gets built.
-
02
Code is cheap once the uncertainty is gone. The decisions are written down and the agent builds on its own.
-
03
Every step is reviewed in a fresh context: the documents against the code before you see them, the code against the documents once it is built.
Five steps. Two are human.
You decide what the agent cannot infer. After that, the loop runs on its own and every step is reviewed in a fresh context. Click the right or left side of the stage, or use the arrow keys.
An idea. You and Claude Code, nothing decided yet.
The loop starts with what the agent cannot infer: the domain, the architecture, the structure.
Nine skills (five are the main loop) and four agents.
The loop 5
You: What we build and why. Agent: It interviews you until nothing blocking is left open; anything the code can answer, it looks up in the code.
You: That the slices are the right ones. Agent: It splits the work into slices that never touch the same file, each with its own check.
You: Nothing: your time in the loop ends here. Agent: It builds the slices in parallel, one agent per slice, passes every check and reviews the whole change.
You: Which proof counts. Agent: It tests the build live, end to end and in a browser when it applies, and records the evidence.
You: One yes. Agent: It reconciles the documentation with what was built, and then commits, pushes and opens a pull request.
When you are lost 1
You: Saying you're lost. Agent: It repeats the last answer until it lands, without moving the work forward.
Above the loop 3
You: Whether it works without you. Agent: Every question a phase would ask you goes to act-as-me, and detached.md keeps them for the morning.
You: Which piece of work to pick up. Agent: It says where each open piece of work stands, where it came from and what the next step is.
You: Showing it or hiding it. Agent: It shows the line above the prompt with the work, the phase, the slices and the agent running now.
The agents 4
You: Nothing. Implement launches it, one per slice. Agent: It builds its slice in a fresh context, changes only the files the slice lists, passes its check and reports.
You: Nothing. Shape, plan and close launch it. Agent: It audits a document in a fresh context and returns every claim the code does not back, with file and line. The evaluator-optimizer pattern: the draft is fixed and audited again.
You: Nothing. Implement launches it. Agent: It tries to refute the change against the documents and the repo's conventions, and returns confirmed, refuted or uncertain, with evidence.
You: Whether you let it answer for you. Agent: In detached mode it answers what a phase would ask you, as a pragmatic senior would: it checks the code first, answers with the why, or says it cannot decide.
The latest releases.
- The craft bar shows the work, the phase and
detachedfor a phase the model starts with the Skill tool, the same as for one you type. Before, a phase started that way (a routine asking in words, a session moving on to the next phase) showed onlycraft. /craft:detachedanswers one line, whether the mode is on or off in this repository, without the line about routines.- The bar draws above the prompt in the terminal and in the desktop app. The web (claude.ai/code) does not draw it.
Detached mode: craft carries a piece of work with nobody at the keyboard.
/craft:detached onturns it on and/craft:detached offends it. A routine starts with/craft:detached onas its first message, or asks for the mode in words, since both/craft:detachedand/craft:barcan now be called by the model.- While it is on, every question a phase would put to you (shape, plan, implement, try and close, approvals and confirmations included) goes to the new agent
craft:act-as-me, which runs on Fable 5.1 in a fresh context and answers as an extremely pragmatic senior software engineer who takes nothing for granted. It checks the code first, answers with one option, given or its own, and why, and saysCannot decidewith what is missing instead of inventing. When it cannot decide, or does not start, the phase stops and names the question. - The mode is the flag
craft.detachedin the repository's local git config: per repository, outside the tree, never committed. - Each answer is appended to
detached.mdin the work's folder with its phase, the question, the answer and why, in order. It is the file to read in the morning, next to the pull request. - Close commits, pushes and opens the pull request when
craft:act-as-mesays yes. The yes is logged indetached.mdbefore the commit, so the commit carries it, and close says who gave it. You review the pull request. - The craft bar shows
detachedafter the phase while the mode is on, and ends with anxthat hides it, the same as/craft:bar off. - Four evals grade the detached path of shape, plan, try and close on the trace and the files: no
AskUserQuestioncall,craft:act-as-mestarted for the questions, the entry indetached.md. - Without the flag the human answers every question, as before. Every rule now asks as
references/ask.mdsays, instead of naming the human orAskUserQuestionitself.