plan2doclisted

Create an implementation plan for: $ARGUMENTS Current changes: !`git diff --stat` Existing research (if any): !`ls -t .simple-workflow/docs/research/*.md 2>/dev/null | head -5` Invocation policy: Do not auto-invoke. Only invoke when explicitly called by name by the user or by another skill (e.g. `/scout` Step 7). `disable-model-invocation: false` is intentional because this skill is chain-called from `/scout` by name via the Skill tool; flipping to `true` breaks the chain-call surface for `/scout` and any direct `/plan2doc <feature>` user invocation. ## Pre-computed Context Available user skills: !`( ls -1 ~/.claude/skills 2>/dev/null ; ls -1 .claude/skills 2>/dev/null ) | sort -u | grep . | tr "\n" "," | sed "s/,$//" | grep . || echo "(none)"` Available MCP servers: !`( jq -r '.mcpServers // {} | keys[]' .mcp.json 2>/dev/null ; jq -r '.mcpServers // {} | keys[]' ~/.claude.json 2>/dev/null ) | sort -u | grep . | tr "\n" "," | sed "s/,$//" | grep . || echo "(none)"` ## Mandatory Skill Invocations The following agent invocation is **contractual** — `/plan2doc` MUST delegate to the `planner` agent via the Agent tool. `/plan2doc` itself writes no plan content; its entire role is to detect Size, resolve the output destination, and spawn the `planner` agent with the appropriate model (sonnet for S, opus for M/L/XL). Any bypass is a contract violation and will be detected by the skill invocation audit (Phase A+). | Invocation Target | When | Skip consequence | |---|---|---|