From honcho
First-time Honcho configuration -- set API key, validate connection, create config
How this skill is triggered — by the user, by Claude, or both
Slash command
/honcho:setupThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Walk the user through first-time Honcho configuration so persistent memory works in Claude Code.
Walk the user through first-time Honcho configuration so persistent memory works in Claude Code.
Check if HONCHO_API_KEY is set as an environment variable OR if ~/.honcho/config.json already has an apiKey:
bun -e "
const fs = require('fs');
const path = require('path');
const configPath = path.join(require('os').homedir(), '.honcho', 'config.json');
const envKey = process.env.HONCHO_API_KEY;
let configKey = '';
try { configKey = JSON.parse(fs.readFileSync(configPath, 'utf-8')).apiKey || ''; } catch {}
console.log(envKey || configKey ? 'set' : 'not set');
"
If the output is set, skip to step 3 (validation). Otherwise continue.
Tell the user to get a free API key at https://app.honcho.dev, then set it as an environment variable.
Detect the platform and give the appropriate command:
If Windows (check with bun -e "console.log(process.platform)" if unsure):
Set your API key in PowerShell:
setx HONCHO_API_KEY "your-key-here"Then restart Claude Code and run
/honcho:setupagain.
If macOS / Linux:
Add to your shell config (
~/.zshrcor~/.bashrc):export HONCHO_API_KEY="your-key-here"Then restart Claude Code and run
/honcho:setupagain.
IMPORTANT: Do NOT ask the user to paste their API key into the chat. Keys must be set via environment variable outside of Claude Code.
Stop here and wait for the user to come back after restarting. Do not proceed to validation until the user runs /honcho:setup again.
Run the setup runner to validate the connection:
bun run "${CLAUDE_PLUGIN_ROOT}/src/skills/setup-runner.ts"
If CLAUDE_PLUGIN_ROOT is not set, resolve the path:
bun -e "const h=require('os').homedir();const p=require('path');console.log(p.join(h,'.claude','plugins','cache','honcho','honcho'))"
Then find the version directory inside that path and run the setup runner from there.
If it succeeds, the key is valid and the full config file has been created. The
runner also installs the memory statusLine: it copies the renderer to
~/.honcho/honcho-statusline.sh and registers it in ~/.claude/settings.json
(only when no statusLine is already configured — an existing one is left
untouched and the path is printed for manual use). Toggle visibility later with
the statusline key in ~/.honcho/config.json: on (default) or off.
If it fails, help the user troubleshoot:
Tell the user that Honcho is configured and memory will be active on their next session. Suggest they restart Claude Code to see the memory context load.
npx claudepluginhub vshuraeff/claude-honcho --plugin honchoGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Implements work from a spec or tickets using TDD at agreed seams, with regular typechecking and test runs, followed by code review.