How this skill is triggered — by the user, by Claude, or both
Slash command
/honcho:configThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Interactive configuration for the Honcho memory plugin. Uses AskUserQuestion for all menus and selections — never dump numbered text lists.
Interactive configuration for the Honcho memory plugin. Uses AskUserQuestion for all menus and selections — never dump numbered text lists.
Call get_config to load the current state. The response includes a card field — a pre-rendered box-drawing card with perfect alignment.
Output the card value exactly as-is inside a code fence. Do not modify it, re-render it, or add any formatting. Just wrap it in triple backticks:
```
{card value here, verbatim}
```
configExists is false, tell the user no config exists and offer to create one.Present ONE question with these options (the user can select "Other" to reach advanced settings):
AskUserQuestion:
question: "What would you like to configure?"
header: "Config"
options:
- label: "Peers"
description: "Your name and AI name (currently: {resolved.peerName} / {resolved.aiPeer})"
- label: "Session mapping"
description: "How sessions are named — per directory, git branch, or per chat (currently: {resolved.sessionStrategy})"
- label: "Workspace"
description: "Data space and session scope (currently: {resolved.workspace})"
If the user selects "Other", present advanced options:
AskUserQuestion:
question: "Advanced settings:"
header: "Advanced"
options:
- label: "Host"
description: "Platform / local / custom URL (currently: {current.host})"
- label: "Context refresh"
description: "TTL, message threshold, dialectic settings"
- label: "Message upload"
description: "Token limits, summarization settings"
- label: "Statusline"
description: "Memory statusLine visibility — on / off (currently: {resolved.statusline})"
Always include current values in the description so the user can see what's set.
When selected, use AskUserQuestion to ask which peer to change:
AskUserQuestion:
question: "Which peer to change?"
header: "Peers"
options:
- label: "Your name"
description: "Currently: {resolved.peerName}"
- label: "AI name"
description: "Currently: {resolved.aiPeer}"
Then ask for the new value. Call set_config with peerName or aiPeer.
Use AskUserQuestion to ask for the new value if there are known options, otherwise ask the user to type it. Call set_config with the appropriate field. Show the result.
AskUserQuestion:
question: "Which session mapping strategy?"
header: "Sessions"
options:
- label: "per-directory (Recommended)"
description: "{peer}-{repo} — one session per project"
- label: "git-branch"
description: "{peer}-{repo}-{branch} — session follows branch"
- label: "chat-instance"
description: "chat-{id} — fresh each launch"
Do NOT use markdown previews for this menu — descriptions are sufficient and previews truncate in narrow terminals.
After strategy selection, ask about peer prefix:
AskUserQuestion:
question: "Include your name in session names?"
header: "Prefix"
options:
- label: "Yes — {peerName}-{repoName}"
description: "For teams sharing a workspace"
- label: "No — {repoName} only"
description: "Cleaner for solo use"
When selected, present a sub-menu:
AskUserQuestion:
question: "Workspace settings?"
header: "Workspace"
options:
- label: "Rename workspace"
description: "Change workspace name (currently: {resolved.workspace})"
Dangerous field — requires confirmation. First call set_config WITHOUT confirm: true. The tool will return a description of what will happen. Use AskUserQuestion to confirm:
AskUserQuestion:
question: "Switch workspace to '{value}'?"
header: "Confirm"
options:
- label: "Yes, switch"
description: "Change to the new workspace"
- label: "Cancel"
description: "Keep current workspace"
If confirmed, call set_config again WITH confirm: true.
Host changes require confirmation. First call set_config WITHOUT confirm: true. The tool will return a description of what will happen. Use AskUserQuestion to confirm, then call again WITH confirm: true.
Use AskUserQuestion to pick which setting to change:
AskUserQuestion:
question: "Which context refresh setting?"
header: "Refresh"
options:
- label: "TTL"
description: "Cache lifetime — currently {contextRefresh.ttlSeconds}s (default: 300)"
- label: "Message threshold"
description: "Refresh every N messages — currently {contextRefresh.messageThreshold} (default: 30)"
- label: "Skip dialectic"
description: "Skip chat() in prompt hook — currently {contextRefresh.skipDialectic} (default: false)"
Then ask for the new value and call set_config.
AskUserQuestion:
question: "Memory statusLine visibility?"
header: "Statusline"
options:
- label: "on (Recommended)"
description: "Sync status, clickable session link, and live activity"
- label: "off"
description: "Hidden"
Call set_config with field statusline and the chosen value. Takes effect on the next statusLine repaint.
Use AskUserQuestion to pick which setting to change:
AskUserQuestion:
question: "Which message upload setting?"
header: "Upload"
options:
- label: "Max user tokens"
description: "Truncate user messages — currently {messageUpload.maxUserTokens || 'no limit'}"
- label: "Max assistant tokens"
description: "Truncate assistant messages — currently {messageUpload.maxAssistantTokens || 'no limit'}"
- label: "Summarize assistant"
description: "Use summary instead of full text — currently {messageUpload.summarizeAssistant}"
Then ask for the new value and call set_config.
After handling a selection, call get_config again to refresh state. Use AskUserQuestion to ask if they want to configure more:
AskUserQuestion:
question: "Configuration updated. What next?"
header: "Next"
options:
- label: "Configure more"
description: "Return to settings menu"
- label: "Done"
description: "Exit configuration"
If "Configure more", go back to Step 2. If "Done", show the final status header and exit.
set_config including any cache invalidation that occurred.get_config returns configExists: false, guide the user to set HONCHO_API_KEY first.npx claudepluginhub outpoints/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.
2plugins reuse this skill
First indexed Jul 18, 2026