titanium-work

A command that runs a development project through several phases by assigning tasks to specialised coding agents and tracking the work.

In plain words
What is it for?
Use it to carry out a multi-step software task involving areas such as APIs, frontend code, deployment, testing, debugging, and security.
Why use it?
It coordinates planning, implementation, testing, security checks, and reviews so the workflow does not have to be managed manually.

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-work
Clone the repo
git clone --depth 1 https://github.com/webdevtodayjason/titanium-plugins
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,407 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 $0.00010 $0.06407
Opus 5 $0.00005 $0.03204
Sonnet 5 $0.00002 $0.01281
Haiku 4.5 $0.00001 $0.00641

Measured yesterday against content hash a44eab8e7314, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

titanium-work 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 yesterday.

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-work.md · 1,097 lines

How it starts

The opening of the file, as written. The whole thing — 1,097 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Titanium Work Command

You are orchestrating a complete development workflow. This command coordinates multiple specialized subagents, manages state transitions, validates quality at each step, and stores progress in Pieces LTM.

Orchestration Model: You delegate implementation tasks to specialized development agents (api-developer, frontend-developer, devops-engineer, etc.) who each have deep domain knowledge via skills. Each agent works in a separate context window with access to relevant expertise.

Agents & Their Skills:

  • @api-developer: api-best-practices, testing-strategy, security-checklist
  • @frontend-developer: frontend-patterns, testing-strategy, technical-writing
  • @devops-engineer: devops-patterns, security-checklist
  • @code-reviewer: code-quality-standards, security-checklist, testing-strategy
  • @security-scanner: security-checklist, code-quality-standards
  • @tdd-specialist: testing-strategy, code-quality-standards
  • @test-runner: testing-strategy, debugging-methodology
  • @debugger: debugging-methodology, testing-strategy

MCP Tools Used: This command uses the tt MCP server for plan generation:

  • mcp__plugin_titanium-toolkit_tt__plan_parser - Requirements → Implementation plan

Overview

This workflow has 5 phases:

  1. Pre-Flight: Validate setup and check for existing plan
  2. Planning: Create plan if needed (or use existing)
  3. Implementation: Execute tasks sequentially with specialized agents
  4. Review: Quality check with parallel review agents
  5. Completion: Finalize and summarize

Voice hooks will announce progress automatically throughout.


Phase 1: Pre-Flight Checks

1.1 Determine Project Path

# Get current working directory
pwd

Use this as the project_path for all subsequent operations.

1.2 Check for Existing Plan

# Check if plan exists
ls .titanium/plan.json

If plan.json exists:

  • Read it with Read tool
  • Ask user: "I found an existing plan. Would you like to use it or create a new one?"
  • If user says use existing → Skip to Phase 3 (Implementation)
  • If user says create new → Continue to Phase 2 (Planning)

Read the full file on GitHub · 1,097 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. yesterday First seen · 1,097 lines · 10 tokens per session scan A a44eab8e7314

Subscribe to this mod's changes

titanium-work is a command published in the GitHub repository webdevtodayjason/titanium-plugins (7 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 6,407 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.