mem:init
Compatibility: If
AskUserQuestionis unavailable, present options as a numbered list and wait for the user's reply. IfTaskis unavailable, run parallel steps sequentially. Thecontext: forkandagent:frontmatter fields are Claude Code-specific — on OpenCode and VS Code Copilot they are ignored and the skill runs inline using the current model.
One-time project bootstrap. Sets up CLAUDE.md (and optionally AGENTS.md) so that
team knowledge loads automatically at session start.
Step 1: Check if Already Configured
Search CLAUDE.md for mem list or ## Team Knowledge.
If found, report:
Already configured -- CLAUDE.md already has a mem section.
Stop here.
Step 2: Write CLAUDE.md Block
If CLAUDE.md does not exist, create it. Append the following block:
## Team Knowledge
At the start of every session, load project knowledge into context:
\`\`\`bash
npx @codevoyant/agent-kit mem list
\`\`\`
Step 3: Ask About AGENTS.md
AskUserQuestion:
question: "Also add to AGENTS.md for OpenCode/Copilot compatibility?"
options:
- "Yes -- add to AGENTS.md too"
- "No -- CLAUDE.md only"
If yes, write the same block to AGENTS.md (create if missing, append if exists).
Step 4: Ask About Claude Code Hook
AskUserQuestion:
question: "Add a Claude Code hook to auto-load team knowledge on session start?"
options:
- "Yes -- add to .claude/settings.json"
- "No -- I'll call it manually or via CLAUDE.md"
If hook selected, read .claude/settings.json (create if missing). Merge a UserPromptSubmit hook:
{
"hooks": {
"UserPromptSubmit": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "npx @codevoyant/agent-kit mem list 2>/dev/null || true"
}
]
}
]
}
}
Preserve any existing settings/hooks when merging.
Step 5: Report
mem:init complete
CLAUDE.md updated -- team knowledge will load every session.
Run /mem:learn to add your first piece of knowledge.
Or: npx @codevoyant/agent-kit mem learn
More from cloudvoyant/codevoyant
mem:help
Use when the user asks about available mem commands or needs help choosing a skill. Triggers on: \"mem help\", \"help mem\", \"what can mem do\", \"mem commands\", \"list mem skills\", \"mem reference\". Lists all mem commands with descriptions, arguments, and usage guidance.
14dev:plan
Use when planning architecture for a project or feature. Triggers on: "dev plan", "architecture plan", "plan architecture", "design architecture", "technical design", "system design for". Produces draft plan artifacts in .codevoyant/plans/{slug}/. Use /dev:approve to promote to docs/architecture/.
14em:review
Use when reviewing an engineering roadmap for quality and realism. Triggers on: "em review", "review roadmap", "sanity check roadmap", "em check", "review this plan". Checks capacity realism, dependency gaps, missing risks, and phasing quality. Auto-launched after em:plan.
13ux:prototype
Use when creating a UX prototype or interactive mockup. Triggers on: \"ux prototype\", \"create prototype\", \"scaffold prototype\", \"build prototype\", \"new prototype\", \"prototype this\". Scaffolds a SvelteKit + Tailwind + shadcn-svelte app with feature-slice architecture. Hard-coded data, fake auth, professional design.
12em:update
Use when modifying an existing em plan or task files. Triggers on: \"update em\", \"change plan\", \"modify epic\", \"add task\", \"remove task\", \"rename phase\", \"apply annotations\", \"edit plan\". Applies inline > and >> annotations or accepts conversational changes to plan.md or task milestone files.
12spec:go
Use when executing or continuing a spec plan interactively. Triggers on: "spec go", "execute plan", "run plan", "continue plan", "work on plan", "start plan", "run the spec". Runs tasks with configurable breakpoints for review. Pass --bg for fully autonomous background execution.
12