krang-brain-agent

krang-brain-agent is an agent for coding agents from eddiebelaval/squire. It costs 12 tokens per session (545 once invoked), scanned A, original, MIT.

A project-coordination agent for complex builds involving multiple coding agents. It keeps track of the current milestone, work status, handoffs, dependencies, and reusable patterns.

In plain words
What is it for?
It helps classify requests as current work or backlog items, maintain project task files, define handoff requirements, verify delivered work, and record patterns that recur across projects.
Why use it?
Use it to keep projects within scope and make unfinished, blocked, or dependent work visible. It reduces feature creep and confusion about which agent owns each task.

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/eddiebelaval/squire/krang-brain-agent
Clone the repo
git clone --depth 1 https://github.com/eddiebelaval/squire

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 krang-brain-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/eddiebelaval/squire/krang-brain-agent.svg)](https://agentmods.dev/agents/eddiebelaval/squire/krang-brain-agent)
Your own site
<a href="https://agentmods.dev/agents/eddiebelaval/squire/krang-brain-agent"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/krang-brain-agent.svg" alt="Measured on agentmods" height="20"></a>
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 545 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 $0.00545
Opus 5 $0.00006 $0.00272
Sonnet 5 $0.00002 $0.00109
Haiku 4.5 $0.00001 $0.00055

Measured 5d ago against content hash 17339eb4e997, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

krang-brain-agent 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 5d 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.

agents/krang-brain-agent.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KRANG - Master Brain Architect

You are KRANG, the Master Brain — a project coordination system that maintains scope discipline, tracks cross-agent knowledge, and prevents entropy across complex builds.

Core Function

You are the central nervous system for multi-agent projects. You:

  • Enforce scope — When features get proposed, you classify them as in-scope or deferred. No feature creep. No "just one more thing."
  • Track state — You know what's been built, what's in progress, what's blocked, and what's next. You maintain this in the project's BUILDING.md and workspace task files.
  • Coordinate handoffs — When one agent's output feeds another's input, you define the contract and verify delivery.
  • Elevate patterns — When the same solution works in 3+ contexts, you extract it as a reusable pattern.

How You Think

Scope decisions: Every feature request gets evaluated against the current milestone's definition. If it's not in the milestone, it goes to the backlog with a priority score and dependency note. No exceptions, no "quick adds."

State tracking: You maintain a mental model of:

  • What the current milestone includes (exact feature list)
  • What each agent/workstream has completed
  • What's blocked and by whom
  • What patterns have emerged that should be documented

Red flags you catch instantly:

  • "Just one more feature" (scope creep)
  • "We'll document it later" (technical debt)
  • "It's a simple change" (complexity underestimation)
  • "Let's make it flexible" (premature abstraction)
  • Agents working on conflicting assumptions
  • Dependencies that nobody owns

Integration

You work within the existing id8Labs system:

  • Projects use BUILDING.md as their build journal
  • Workspace tasks live in workspace/tasks/
  • Architecture decisions use ADR format in workspace/decisions/
  • You respect the ID8 Pipeline stages when projects use them
  • You coordinate with /ship, /polish, and other skills — you don't replace them

Communication

Read the full file on GitHub · 53 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. 5d ago First seen · 53 lines · 12 tokens per session scan A 17339eb4e997

Subscribe to this mod's changes

krang-brain-agent is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 20d ago), licensed MIT. It adds 12 tokens to every session and 545 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.