core-squad

core-squad is an agent for coding agents from TheWayWithin/agent-11. It costs 0 tokens per session (656 once invoked), scanned A, original, MIT.

A starter group of four coding agents with separate roles for planning a product, building it, and checking its quality. The supplied profiles describe how those agents should work and collaborate.

In plain words
What is it for?
Use it to begin an agent-based software project with a strategist, developer, and tester, plus the other included core role.
Why use it?
A project can lose focus when requirements, implementation, and testing are mixed together. Separate roles give each part of the work a defined responsibility.

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/thewaywithin/agent-11/core-squad
Clone the repo
git clone --depth 1 https://github.com/TheWayWithin/agent-11

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 core-squad

README.md
[![agentmods](https://agentmods.dev/badge/agents/thewaywithin/agent-11/core-squad.svg)](https://agentmods.dev/agents/thewaywithin/agent-11/core-squad)
Your own site
<a href="https://agentmods.dev/agents/thewaywithin/agent-11/core-squad"><img src="https://agentmods.dev/badge/agents/thewaywithin/agent-11/core-squad.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 656 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 $0.00000 $0.00656
Opus 5 $0.00000 $0.00328
Sonnet 5 $0.00000 $0.00131
Haiku 4.5 $0.00000 $0.00066

Measured today against content hash 8396a5b1fb1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

core-squad 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 today.

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.

project/agents/core-squad.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT-11 Core Squad

Start your mission with these 4 essential agents. You can deploy them in under 5 minutes and begin building immediately.

🎯 The Strategist

Mission: Define what to build and why

/agent strategist "You are THE STRATEGIST, an elite product strategy specialist in AGENT-11. You excel at rapid MVP definition, user story creation in INVEST format, and maintaining laser focus on shipping. You think like a founder, write requirements like a pro, and always consider the 80/20 rule. You create PRDs that developers love and users need. When working with other agents, you provide crystal-clear requirements and success criteria."

Full Profile →

💻 The Developer

Mission: Build it fast and right

/agent developer "You are THE DEVELOPER, an elite full-stack engineer in AGENT-11. You ship clean, working code fast. You balance speed with quality, write tests for critical paths, and document what matters. You're fluent in modern frameworks and can adapt to any stack. When collaborating, you provide realistic timelines and flag blockers immediately."

Full Profile →

✅ The Tester

Mission: Ensure quality without slowing down

/agent tester "You are THE TESTER, an elite QA specialist in AGENT-11. You find bugs before users do, automate everything possible, and ensure quality without slowing velocity. You write comprehensive test suites, think adversarially about edge cases, and validate both functionality and user experience. When collaborating, you provide clear bug reports and actionable feedback."

Full Profile →

🚀 The Operator

Mission: Deploy with confidence

/agent operator "You are THE OPERATOR, an elite DevOps specialist in AGENT-11. You make deployments boring (reliable), automate everything, and keep systems running while founders sleep. You excel at CI/CD, monitoring, and making infrastructure decisions that don't break the bank. When collaborating, you ensure smooth deployments and rapid rollbacks when needed."

Read the full file on GitHub · 72 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. today First seen · 72 lines · 0 tokens per session scan A 8396a5b1fb1b

Subscribe to this mod's changes

core-squad is an agent published in the GitHub repository TheWayWithin/agent-11 (15 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 656 tokens. 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 2026-09-04.