speckit.squad.init

A command that creates a Squad team of coding agents from an implementation plan. Squad is a tool for dividing software work among specialized agents based on the project's technologies and development stages.

In plain words
What is it for?
It helps initialize a team after running /speckit.plan, using the plan, specification, and optional task list to shape the team.
Why use it?
It turns the technical decisions in a plan into agent roles and routing rules, so work can be assigned with more project-specific context.

Agent

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 agents/sabbour/agentweaver/speckit.squad.init
Clone the repo
git clone --depth 1 https://github.com/sabbour/agentweaver
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,106 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 $0.00012 $0.01106
Opus 5 $0.00006 $0.00553
Sonnet 5 $0.00002 $0.00221
Haiku 4.5 $0.00001 $0.00111

Measured 2d ago against content hash 29ea04c9e996, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speckit.squad.init 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.

.github/agents/speckit.squad.init.agent.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Squad Bridge: Init

Read the implementation plan and bootstrap a Squad team tailored to its technology stack, architecture layers, and implementation phases. Run this once after your initial /speckit.plan to get a squad that mirrors your project's concrete technical shape.

Why plan and not spec? The spec (spec.md) is intentionally tech-agnostic — it captures goals, users, and constraints. The plan (plan.md) is where concrete technology decisions live (e.g., "React 19 with Next.js", "Go API with gin"). Generating agents from the plan produces sharper charters with accurate capabilities and routing rules.

Prerequisites

Verify Squad CLI is available:

squad --version

If that fails, install it first:

npm install -g @bradygaster/squad-cli

User Input

$ARGUMENTS

Steps

  1. Read the plan from the active spec directory under specs/ (e.g., specs/001-<name>/plan.md). If no plan exists, tell the user to run /speckit.plan first and stop. Also read spec.md for supplementary context (goals, constraints, non-functional requirements).

  2. Read tasks from specs/<id>/tasks.md if it exists (used to infer work types and routing signals).

  3. Load bridge config from .specify/extensions/squad/squad-config.yml if it exists, otherwise use extension defaults.

  4. Analyze the plan to extract:

    • Technology stack explicitly chosen (e.g., "React 19 with Next.js", "Go microservices with gin", "PostgreSQL with Prisma ORM")
    • Architecture layers (frontend, backend, API gateway, data layer, infra)
    • Implementation phases (if the plan defines phased delivery)
    • Cross-cutting concerns (e.g., auth, testing, documentation, CI/CD)
    • Any explicit roles or team structure mentioned in the plan or spec
  5. Initialize Squad if .squad/ does not already exist:

    squad init
    
  6. Generate agent definitions — for each identified domain/concern, create a Squad agent with:

    • A descriptive name (e.g., backend-engineer, frontend-engineer)
    • A role derived from the domain
    • capabilities array (name + level: expert/proficient/basic) inferred from how prominently the domain features in the plan
    • model set to the tier from config that matches the agent's complexity
    • status: active

Read the full file on GitHub · 119 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 · 119 lines · 12 tokens per session scan A 29ea04c9e996

Subscribe to this mod's changes

speckit.squad.init is an agent published in the GitHub repository sabbour/agentweaver (5 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 1,106 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 2026-08-31.