parallel-executionlisted
Install: claude install-skill nxtg-ai/forge-plugin
# Parallel Execution: Plan Mode + Agent Teams
Two superpowers. **Plan Mode** thinks before it writes. **Agent Teams** fan work out
across parallel subagents. Combine them for complex features. The agent roster and
routing rules in §5 are the source of truth for `Task` delegation — the `subagent_type`
must match a `name:` from that table exactly.
## 1. PLAN MODE
```
Explore (reads only) → Draft plan → Present → Wait for approval → Execute
```
1. **Explore only** — Read, Glob, Grep, read-only Bash. No writes until approved.
2. **Draft a plan** — scope, files affected, approach, boundaries.
3. **Present** — show the plan in chat, ask for approval.
4. **Wait** — do not proceed until the user says "proceed" / "yes" / "looks good".
5. **Execute** — now write, edit, spawn agents.
### Plan document format
```
## Plan: {task name}
**Scope:** what will change
**Files to create / modify / NOT touch:** (the last is a boundary declaration)
**Approach:** brief
**Risks / trade-offs:** if any
Proceed? (yes / modify / cancel)
```
### When to invoke
| Situation | Plan Mode? |
|-----------|-----------|
| Touching 3+ files | Yes |
| A `--fix` command (show what changes before writing) | Yes — always |
| Architectural change | Yes |
| Single-file bug fix / comment / answering a question | No |
### Anti-patterns
- Writing files during Explore.
- Presenting a plan then executing without waiting.
- Skipping the plan for a "quick" task that touches 3+ files.
- Modifying files outside the de