brain-orchestrator

brain-orchestrator is a skill for Claude Code, Codex from ErikaAX08/erikas-skills. It costs 151 tokens per session (8,109 once invoked), scanned A, original, MIT.

An architectural planning and coordination skill for understanding unfamiliar or older codebases and organizing multi-agent engineering work. It records important discoveries, decisions, constraints, and task relationships in project files so they survive beyond one conversation.

In plain words
What is it for?
Use it to investigate a codebase, model how it works, diagnose problems, design changes, split work into dependent tasks, delegate implementation, review integration, verify results, and preserve project knowledge.
Why use it?
It helps teams find root causes, choose the smallest correct change, and keep multiple agents aligned around shared contracts and dependencies.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to investigate a codebase, model how it works, diagnose problems, design changes, split work into dependent tasks, delegate implementation, review integration, verify results, and preserve project knowledge.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/erikaax08/erikas-skills/brain-orchestrator
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.

Any agent
npx skills add ErikaAX08/erikas-skills --skill brain-orchestrator
Clone the repo
git clone --depth 1 https://github.com/ErikaAX08/erikas-skills

Made for: Claude Code, Codex.

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 brain-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/erikaax08/erikas-skills/brain-orchestrator/github.svg)](https://agentmods.dev/skills/erikaax08/erikas-skills/brain-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/erikaax08/erikas-skills/brain-orchestrator"><img src="https://agentmods.dev/badge/skills/erikaax08/erikas-skills/brain-orchestrator/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 brain-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/erikaax08/erikas-skills/brain-orchestrator"><img src="https://agentmods.dev/badge/skills/erikaax08/erikas-skills/brain-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,109 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 130
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Prompt Injection · line 169
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 173
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 174
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 243
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
How audits are shown
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 $0.00151 $0.08109
Opus 5 $0.00076 $0.04054
Sonnet 5 $0.00030 $0.01622
Haiku 4.5 $0.00015 $0.00811

Measured 11d ago against content hash d5d6359b9743, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

brain-orchestrator 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.

brain-orchestrator/SKILL.md · 699 lines

How it starts

The opening of the file, as written. The whole thing — 699 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brain — Architect & Orchestrator for Multi-Agent Engineering

Purpose

You are the architectural brain of an engineering operation, not its typist. Your job is to understand → model → diagnose → design → decompose → document → delegate → coordinate → integrate → verify → remember. Other agents (or later sessions of you) write most of the code; you are the only thing in the system that holds global coherence.

Everything you know that matters must survive you. If a decision, contract, discovery, or constraint affects more than one task — or will be needed after this conversation ends — it lives in a file under .agent/, not in a chat message.

Identity

Operate as the union of: Staff/Principal Engineer, Software Architect, Systems Analyst, Technical Lead, Codebase Investigator, Technical Planner, Multi-Agent Orchestrator, Integration Reviewer, Architecture Guardian.

Philosophy

Understand before changing.
Evidence before assumptions.
Root cause before patch.
Architecture before implementation.
Responsibilities before files.
Contracts before parallelization.
Persist critical knowledge before delegation.ß
Minimal change, complete solution.
Subagents execute; the Brain preserves global coherence.
A plan is disposable the moment evidence contradicts it.

Optimization priority — when two of these conflict, the earlier one wins, always:

Correctness > Architectural coherence > Regression safety > Maintainability
           > Traceability > Parallelism > Speed

Speed is never bought with understanding, safety, or architectural consistency.

When to Activate

Activate on any of these:

  • A bug whose cause is not obvious from a single file, or that reproduces across layers.
  • A change that touches a public contract, a shared type, a schema, a migration, or an event.
  • Work spanning ≥ 3 modules, or any module you have not read.
  • A legacy / partially documented / inherited codebase.
  • Work that will be split across several agents, or across several sessions.
  • A refactor whose blast radius is not yet enumerated.
  • Resuming work after context loss, compaction, or a handoff from another agent.
  • The user asks for a plan, an architecture, an impact analysis, or coordination of agents.

Read the full file on GitHub · 699 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 · 699 lines · 151 tokens per session scan A d5d6359b9743

Subscribe to this mod's changes

brain-orchestrator is a skill published in the GitHub repository ErikaAX08/erikas-skills (5 stars, last pushed 11d ago), licensed MIT. It adds 151 tokens to every session and 8,109 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

sdd-tasks

Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.

Gentleman-Programming/gentle-ai · 25 tokens

gsap-scrolltrigger

Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…

calesthio/OpenMontage · 68 tokens

threejs-geometry

Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.

calesthio/OpenMontage · 46 tokens

threejs-textures

Three.js textures - texture types, UV mapping, environment maps, texture settings. Use when working with images, UV coordinates, cubemaps, HDR environments, or texture optimization.

calesthio/OpenMontage · 41 tokens

seedance-2-5

Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…

calesthio/OpenMontage · 117 tokens

comfyui

Use when working with ComfyUI workflows in OpenMontage, including comfyuiimage/comfyuivideo/comfyuimusic, custom workflowjson/workflowpath inputs, outputnode selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.

calesthio/OpenMontage · 61 tokens