squad-plan

A command for splitting a large coding task into parallel workstreams for Claude Squad, a setup where multiple coding-agent sessions coordinate on one project.

In plain words
What is it for?
Planning two to five coordinated workstreams, assigning roles, defining owned files or components, and listing the tasks and dependencies for each agent.
Why use it?
It makes dependencies and shared resources explicit before several agents start working. This helps divide work across areas such as frontend, backend, services, or shared code.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/brain-bootstrap/claude-code-brain-bootstrap/squad-plan
Clone the repo
git clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrap

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 735 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00013 $0.00735
Opus 5 $0.00006 $0.00367
Sonnet 5 $0.00003 $0.00147
Haiku 4.5 $0.00001 $0.00073

Measured 2d ago against content hash b902b23fac10, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

squad-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/squad-plan.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate a detailed Claude Squad parallel execution plan for: $ARGUMENTS

ultrathink — use extended reasoning for workstream decomposition and dependency analysis.

Context

Read CLAUDE.md for project architecture, conventions, and critical patterns. Read claude/architecture.md for the workspace layout and service catalog.

Instructions

Phase 1: Analyze the Task

  1. Break down $ARGUMENTS into independent subtasks
  2. Identify natural parallelism boundaries (frontend/backend, services, features, layers)
  3. Map dependencies between subtasks — what must complete before something else can start
  4. Identify shared resources that need coordination (DB schemas, API contracts, shared types)

Phase 2: Design Workstreams

Create 2-5 distinct workstreams, each assignable to a separate Claude Code instance:

For each workstream:

  • Workstream ID & Title — e.g., "WS1: API Layer"
  • Assigned Role — e.g., "Backend API Developer"
  • Objective — what this instance accomplishes
  • Files/Components — the specific parts of the codebase this workstream owns
  • Tasks — numbered checklist items with:
    • Description + specific instructions
    • Follow the Explore → Plan → Act TDD workflow for each coding task
    • Expected outcome
    • Verification steps
  • Dependencies — which tasks from other workstreams must complete first
  • Deliverables — what this workstream produces for other workstreams to consume

Phase 3: Integration Strategy

  1. Define integration points between workstreams
  2. Create integration test checklist
  3. Specify merge order (which branch merges first)
  4. Define smoke test for the combined result

Phase 4: Write ACTION_PLAN.md

Save the plan to claude/tasks/ACTION_PLAN.md with this structure:

# ACTION_PLAN — [Feature Name]

## Overall Objective
[Clear statement of the goal]

## Project Context
[Brief summary — refer to CLAUDE.md for details]

## Workstream Definitions

### WS1: [Title]
**Role:** [Role Name]
**Objective:** [Goal]
**Files:** [List]

#### Tasks
- [ ] Task 1: [Description] — *Explore → Plan → Act*
- [ ] Task 2: ...

**Dependencies:** None (can start immediately)
**Delivers to:** WS2 needs [output] from Task 3

### WS2: [Title]
...

## Integration Points
- [ ] [Integration task 1]
- [ ] [Integration task 2]

## Testing Strategy
- [ ] Unit tests per workstream
- [ ] Integration tests after merge
- [ ] End-to-end smoke test

## Coordination Notes
- Each instance should check off tasks as they complete
- Signal completion by updating this file
- All instances must follow `CLAUDE.md` standards

Read the full file on GitHub · 105 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 105 lines · 13 tokens per session scan A b902b23fac10

Subscribe to this mod's changes

squad-plan is a command published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 735 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.