speckit.squad.run

speckit.squad.run is an agent for coding agents from sabbour/agentweaver. It costs 7 tokens per session (1,173 once invoked), scanned A, original, MIT.

A command that sends routed Speckit tasks to Squad agents for execution. Squad agents are separate coding-agent sessions assigned to particular kinds of work.

In plain words
What is it for?
Use it after tasks have been routed to active Squad agents. It can run pending routed tasks, create branches, and optionally create pull requests.
Why use it?
It connects task assignments with actual implementation work. It also checks that the required task routing, agents, command-line tools, and GitHub authentication are available.

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.run
Clone the repo
git clone --depth 1 https://github.com/sabbour/agentweaver

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for speckit.squad.run

README.md
[![agentmods](https://agentmods.dev/badge/agents/sabbour/agentweaver/speckit.squad.run.svg)](https://agentmods.dev/agents/sabbour/agentweaver/speckit.squad.run)
Your own site
<a href="https://agentmods.dev/agents/sabbour/agentweaver/speckit.squad.run"><img src="https://agentmods.dev/badge/agents/sabbour/agentweaver/speckit.squad.run.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,173 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 $0.00007 $0.01173
Opus 5 $0.00003 $0.00587
Sonnet 5 $0.00001 $0.00235
Haiku 4.5 $0.00001 $0.00117

Measured 3d ago against content hash 13f3b92e360f, 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.run 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 3d 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.run.agent.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Squad Bridge: Run

Execute routed tasks by spawning Squad agent sessions. Reads the task list and agent assignments produced by /speckit.squad.route, then launches agents to do the work — creating branches, running sessions, and optionally creating PRs.

This is the command that closes the loop: specs become plans, plans become tasks, tasks get routed to agents, and this command makes agents execute.

Prerequisites

  • Tasks must be routed: run /speckit.squad.route --update-tasks first
  • Squad CLI available: squad --version
  • GitHub CLI authenticated: gh auth status

User Input

$ARGUMENTS

Steps

  1. Read tasks from specs/<id>/tasks.md. Identify tasks that have squad routing metadata (comments like <!-- squad:agent=backend-engineer tier=standard -->). If no routed tasks found, tell the user to run /speckit.squad.route --update-tasks first and stop.

  2. Load Squad agents from .squad/agents/ and verify each assigned agent exists and has status: active.

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

  4. Parse arguments:

    • No args: run all pending routed tasks
    • Task ID or title fragment (e.g., task-03): run only that task
    • --dry-run: show what would execute without starting sessions
    • --retry: re-run previously failed tasks only
    • --retry <task-id>: re-run a specific failed task
  5. If --dry-run, print the execution plan and stop:

    Dry Run — would execute:
    ─────────────────────────────────────────────────────────
    Task                              Agent               Tier
    ─────────────────────────────────────────────────────────
    Design REST API endpoints         backend-engineer    full
    Implement JWT authentication      backend-engineer    standard
    Build login form component        frontend-engineer   standard
    Write unit tests for auth         qa-engineer         standard
    ─────────────────────────────────────────────────────────
    4 tasks | 3 agents | parallel limit: 3
    
    Run without --dry-run to execute.
    

Read the full file on GitHub · 136 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. 3d ago First seen · 136 lines · 7 tokens per session scan A 13f3b92e360f

Subscribe to this mod's changes

speckit.squad.run is an agent published in the GitHub repository sabbour/agentweaver (5 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 1,173 once invoked, about $0.0000 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.