titanium-plan

A command that turns project requirements into a detailed implementation plan. It uses the Titanium Toolkit to break work into tasks and assign them to suitable agents.

In plain words
What is it for?
Use it to analyse requirements, create an implementation plan, check that plan, document it, and save it for later reference.
Why use it?
It helps organise large requests before coding begins, so requirements, responsibilities, and implementation steps are written down.

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-plan
Clone the repo
git clone --depth 1 https://github.com/webdevtodayjason/titanium-plugins
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,813 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00007 $0.02813
Opus 5 $0.00003 $0.01406
Sonnet 5 $0.00001 $0.00563
Haiku 4.5 $0.00001 $0.00281

Measured 2d ago against content hash 42502c7de656, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

titanium-plan scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 ~/.env
plugins/titanium-toolkit/commands/titanium-plan.md · 398 lines

How it starts

The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Titanium Plan Command

You are creating a structured implementation plan from requirements. Follow this systematic process to break down work into actionable tasks with agent assignments.

MCP Tools Used: This command uses the tt MCP server (Titanium Toolkit) which provides:

  • mcp__plugin_titanium-toolkit_tt__plan_parser - Generates structured implementation plans from requirements

The tt server wraps Python utilities that use Claude AI to analyze requirements and create detailed project plans with task-to-agent assignments.

Agent Assignment: The plan_parser automatically assigns tasks to appropriate specialized agents based on task type (API work → @api-developer, UI work → @frontend-developer, etc.). These assignments are used by /titanium:work to delegate implementation.

Process Overview

This command will:

  1. Gather and validate requirements
  2. Use Claude (via plan_parser MCP tool) to generate structured plan
  3. Validate plan with vibe-check
  4. Create human-readable documentation
  5. Store plan in Pieces for future reference

Step 1: Gather Requirements

If user provides a file path:

# User might say: /titanium:plan ~/bmad/output/user-auth-prd.md
  • Use Read tool to read the file
  • Extract requirements text

If user provides inline description:

# User might say: /titanium:plan
# Then describe: "I need to add JWT authentication with login, register, password reset"
  • Write description to .titanium/requirements.md using Write tool
  • Ask clarifying questions if needed:
    • What tech stack? (Node.js, Python, Ruby, etc.)
    • What database? (PostgreSQL, MongoDB, etc.)
    • Any specific libraries or frameworks?
    • Security requirements?
    • Performance requirements?

Step 2: Generate Structured Plan

Use the plan_parser MCP tool to generate the plan:

mcp__plugin_titanium-toolkit_tt__plan_parser(
  requirements_file: ".titanium/requirements.md",
  project_path: "$(pwd)"
)

This will:

  • Call Claude with the requirements
  • Generate structured JSON plan with:
    • Epics (major features)
    • Stories (user-facing functionality)
    • Tasks (implementation steps)
    • Agent assignments
    • Time estimates
    • Task dependencies
  • Save to .titanium/plan.json
  • Return the JSON plan directly to Claude

Read the full file on GitHub · 398 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 · 398 lines · 7 tokens per session scan B 42502c7de656

Subscribe to this mod's changes

titanium-plan is a command published in the GitHub repository webdevtodayjason/titanium-plugins (7 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 2,813 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.