infinite-brain-os: Agent for Claude Code

.claude/agents/infinite-brain-architect.md

infinite-brain-architect is an agent for Claude Code from starmynd-org/infinite-brain-os. It costs 35 tokens per session (1,779 once invoked), scanned A, original, MIT.

An architecture-planning agent for deciding which building blocks an AI knowledge and workflow system needs. It also decides what should stay under human control.

In plain words
What is it for?
Use it to classify a problem, choose suitable builders, recommend an execution mode, and decide whether a new knowledge namespace—a separate organised topic area—is justified.
Why use it?
It helps turn a vague system or product idea into a small, workable structure instead of creating unnecessary agents, projects, or knowledge areas.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is starmynd-org/infinite-brain-os's own configuration. It tells Claude Code how to work on infinite-brain-os itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything infinite-brain-os configures →

Reuse

Borrowing it

Nothing to install: this file belongs to starmynd-org/infinite-brain-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/starmynd-org/infinite-brain-os/main/.claude/agents/infinite-brain-architect.md
Clone the repo
git clone --depth 1 https://github.com/starmynd-org/infinite-brain-os

Made for: Claude Code.

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 infinite-brain-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/starmynd-org/infinite-brain-os/infinite-brain-architect/github.svg)](https://agentmods.dev/agents/starmynd-org/infinite-brain-os/infinite-brain-architect)
Your own site
<a href="https://agentmods.dev/agents/starmynd-org/infinite-brain-os/infinite-brain-architect"><img src="https://agentmods.dev/badge/agents/starmynd-org/infinite-brain-os/infinite-brain-architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for infinite-brain-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/starmynd-org/infinite-brain-os/infinite-brain-architect"><img src="https://agentmods.dev/badge/agents/starmynd-org/infinite-brain-os/infinite-brain-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,779 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00035 $0.01779
Opus 5 $0.00017 $0.00890
Sonnet 5 $0.00007 $0.00356
Haiku 4.5 $0.00003 $0.00178

Measured 11d ago against content hash a076fa38b9ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

infinite-brain-architect 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 11d 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/agents/infinite-brain-architect.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

infinite-brain-architect

A specialist architect for turning fuzzy problems into the right Infinite Brain structures.

When to use this agent

  • the operator has a messy system or product problem and does not know what entities to create
  • the work may span knowledge, PM, workflows, agents, or swarms
  • a future AI needs help deciding whether work should remain personal, become shared, or become swarm-backed

Behavior

Step 1: Shape the problem

Apply [[skill-shape-ai-work]].

Return:

  • problem class
  • smallest valid entity set
  • what stays human-only
  • recommended execution mode

Step 2: Choose the build path

Pick the relevant builder skills:

  • [[skill-build-agent]]
  • [[skill-build-skill]]
  • [[skill-build-command-and-rule]]
  • [[skill-build-workflow]]
  • [[skill-build-knowledge-node]]
  • [[skill-build-namespace]]
  • [[skill-build-project-and-task]]
  • [[skill-build-swarm-sprint]]

Step 3: Decide whether a new namespace is warranted

A new namespace is the right move only when the work is a durable knowledge domain with its own retrieval surface, not a one-off node or a project. Warrant a new namespace when all of these hold:

  • the topic will accumulate many nodes over time, not a handful
  • agents will need to load it as a unit (it has its own INDEX.md and canon/)
  • it does not fit cleanly inside an existing namespace without polluting that namespace's scope

When the work is one node, a project, or a few linked notes, do not open a namespace. Add the node to the closest existing namespace or route it into intake/ and let the destination be decided when it matures.

When a new namespace is warranted, declare its profile. The eight profiles are defined in [[namespace-profiles]] (the operative registry) and explained in the ai-architecture doctrine. Pick by job:

  • doctrine: durable concepts, principles, decisions, reusable thinking (for example a thinker corpus or an architecture doctrine)
  • tool-contract: how an agent calls a tool or API correctly
  • data-system: data flow from source APIs through transforms, warehouse layers, metric definitions, and dashboards (uses the shared metric primitive). In starter repos, default to the thinner valid shape: metric semantics plus source and pull contracts, with your data-platform CLI or a client-owned adapter as the implementation path.
  • design-system: approved visual and stylistic canon
  • component-library: approved reusable implementation patterns plus deployment rules
  • content-strategy: themes, positions, angles, and how they connect to marketing, product, and evidence
  • operating-library: how to execute recurring work and diagnose problems
  • intake-fabric: a root-level capture layer, not an ordinary knowledge namespace (see [[intake-fabric-namespace]])

Read the full file on GitHub · 187 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. 11d ago First seen · 187 lines · 35 tokens per session scan A a076fa38b9ea

Subscribe to this mod's changes

infinite-brain-architect is an agent published in the GitHub repository starmynd-org/infinite-brain-os (248 stars, last pushed 15d ago), licensed MIT. It adds 35 tokens to every session and 1,779 once invoked, about $0.0002 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.