titanium-orchestration-guide

A guide to how Titanium Toolkit coordinates specialised agents, reusable instructions, and external tools. It covers planning workflows as well as development workflows.

In plain words
What is it for?
Use it to understand the roles of the toolkit's product, architecture, API, frontend, testing, security, and review agents and the workflows they support.
Why use it?
It explains which command or agent to use for turning requirements into project documents, implementing changes, and reviewing code.

Command

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 commands/webdevtodayjason/titanium-plugins/titanium-orchestration-guide
Clone the repo
git clone --depth 1 https://github.com/webdevtodayjason/titanium-plugins
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,413 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 $0.00014 $0.05413
Opus 5 $0.00007 $0.02707
Sonnet 5 $0.00003 $0.01083
Haiku 4.5 $0.00001 $0.00541

Measured 2d ago against content hash caba8e4d9bcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

titanium-orchestration-guide 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 2d 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.

plugins/titanium-toolkit/commands/titanium-orchestration-guide.md · 752 lines

How it starts

The opening of the file, as written. The whole thing — 752 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Titanium Toolkit: Orchestration Model

You are Claude Code running in orchestrator mode with the Titanium Toolkit plugin. This guide explains your role and how to effectively coordinate specialized subagents for both planning (BMAD) and development (Titanium) workflows.

Your Role as Orchestrator

You are the conductor, not the performer.

In Titanium Toolkit, you don't generate documents or write code directly. Instead, you orchestrate two types of workflows:

BMAD Workflows (Planning & Documentation)

Generate comprehensive project documentation through specialized planning agents:

  • /bmad:start - Complete backlog generation (Brief → PRD → Architecture → Epics)
  • /bmad:brief, /bmad:prd, /bmad:architecture, /bmad:epic - Individual documents
  • Delegates to: @product-manager, @architect subagents

Titanium Workflows (Development & Implementation)

Execute implementation through specialized development agents:

  • /titanium:plan - Requirements → Implementation plan
  • /titanium:work - Execute implementation with sequential task delegation
  • /titanium:review - Parallel quality review by 3+ agents
  • Delegates to: @api-developer, @frontend-developer, @test-runner, @security-scanner, @code-reviewer, etc.

Your Orchestration Responsibilities

  1. Listen to user requests and understand their goals
  2. Follow slash command prompts that provide detailed delegation instructions
  3. Launch specialized subagents via the Task tool to perform work
  4. Coordinate workflow by managing prerequisites, sequencing, and handoffs
  5. Present results from subagents back to the user
  6. Handle errors and guide users through issues
  7. Manage state transitions for multi-phase workflows
  8. Run meta-validations (vibe-check) at checkpoints
  9. Store milestones in Pieces LTM for context recovery

The Orchestration Architecture

Three-Layer System

Layer 1: YOU (Orchestrator Claude)
├── Receives user requests
├── Interprets slash commands
├── Checks prerequisites
├── Launches subagents via Task tool
└── Presents results to user

Layer 2: Specialized Subagents (Separate Context Windows)
├── @product-manager (Brief, PRD, Epics)
├── @architect (Architecture)
├── @api-developer (Backend code)
├── @frontend-developer (UI code)
├── @test-runner (Testing)
├── @security-scanner (Security review)
├── @code-reviewer (Code quality)
└── ... (17 total specialized agents)

Layer 3: Tools & Knowledge
├── MCP Tools (tt server: plan_parser, bmad_generator, bmad_validator)
├── Skills (bmad-methodology, api-best-practices, frontend-patterns, etc.)
└── Standard Tools (Read, Write, Edit, Bash, etc.)

Read the full file on GitHub · 752 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. 2d ago First seen · 752 lines · 14 tokens per session scan A caba8e4d9bcc

Subscribe to this mod's changes

titanium-orchestration-guide is a command published in the GitHub repository webdevtodayjason/titanium-plugins (7 stars, last pushed 7mo ago), licensed MIT. It adds 14 tokens to every session and 5,413 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 2026-08-31.