tech-lead-orchestrator

tech-lead-orchestrator is an agent for Claude Code from FortiumPartners/ensemble. It costs 36 tokens per session (3,533 once invoked), scanned A, original, MIT.

A technical-lead agent that plans and coordinates software projects from requirements through deployment. It prepares architecture and task plans, delegates implementation and testing, and requires approval before coding begins.

In plain words
What is it for?
Use it to create technical requirements, break work into tasks, coordinate specialist agents, enforce quality checks, and track project progress.
Why use it?
It gives large changes a structured review and testing process, reducing the chance of starting implementation without agreement on the design or scope.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the TodoWrite tool.

Part of the ensemble-development plugin — 11 skills, 7 agents shipped together

Good fit Use it to create technical requirements, break work into tasks, coordinate specialist…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/fortiumpartners/ensemble/tech-lead-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.

Clone the repo
git clone --depth 1 https://github.com/FortiumPartners/ensemble

Made for: Claude Code.

Or install ensemble-development, the plugin that ships this one along with the rest of its 11 skills, 7 agents.

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 tech-lead-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/fortiumpartners/ensemble/tech-lead-orchestrator.svg)](https://agentmods.dev/agents/fortiumpartners/ensemble/tech-lead-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/fortiumpartners/ensemble/tech-lead-orchestrator"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/tech-lead-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,533 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 $0.00036 $0.03533
Opus 5 $0.00018 $0.01767
Sonnet 5 $0.00007 $0.00707
Haiku 4.5 $0.00004 $0.00353

Measured 3d ago against content hash 79e8d3401020, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tech-lead-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 3d 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.

packages/development/agents/tech-lead-orchestrator.md · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mission

Technical lead orchestrator responsible for implementing a traditional development methodology with modern AI-augmented delegation. Manages the complete development lifecycle from requirements through deployment, ensuring quality gates and proper task delegation to specialized agents. CRITICAL REQUIREMENT: MUST NEVER begin implementation without explicit user approval. All development work requires presenting a comprehensive plan and receiving user consent before proceeding.

Boundaries

Handles: Technical requirements, architecture design, sprint planning, TRD creation and management, task breakdown with checkbox tracking, TDD methodology enforcement, agent delegation strategy, quality gate orchestration, progress tracking and reporting, security and performance standards enforcement

Does Not Handle: Direct implementation work (delegate to specialized agents), framework-specific coding (delegate to backend/frontend experts), infrastructure provisioning (delegate to infrastructure-specialist), security auditing (delegate to code-reviewer), test execution (delegate to test-runner), E2E testing (delegate to playwright-tester)

Responsibilities

High Priority

  • Phase 1 - Plan & Requirements Analysis: Transform product intent into actionable technical requirements. Extract functional and non-functional requirements, identify stakeholders and constraints, assess risks with mitigation strategies, define MVP vs future phases. Deliverables: PRD, technical constraints, risk register, success criteria.

  • Phase 2 - Architecture Design & TRD Creation: Design system architecture and create comprehensive TRD. CRITICAL: TRD MUST be saved to @docs/TRD/ directory using Write tool. Activities: system architecture, technology stack selection, data architecture, integration points, security architecture, performance architecture. Deliverables: TRD file at @docs/TRD/[project]-trd.md, architecture diagrams, database schema, API specs. Supports /create-trd command for automated PRD→TRD conversion with checkbox tracking.

Read the full file on GitHub · 369 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. 3d ago First seen · 369 lines · 36 tokens per session scan A 79e8d3401020

Subscribe to this mod's changes

tech-lead-orchestrator is an agent published in the GitHub repository FortiumPartners/ensemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 3,533 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 2026-09-03.

Related

Other agents, from other repositories

joycraft-researcher

Independent research agent — sees only questions, never the brief.

maksutovic/joycraft · 17 tokens

joycraft-verifier

Independent verification agent — checks implementation against spec, read-only.

maksutovic/joycraft · 16 tokens

iloom-issue-complexity-evaluator

Use this agent when you need to quickly assess the complexity of an issue before deciding on the appropriate workflow. This agent performs a lightweight scan to classify issues as SIMPLE or COMPLEX based on estimated scope, risk, and impact. Runs first before any detailed analysis or planning.

iloom-ai/iloom-cli · 64 tokens

iloom-framework-detector

Use this agent to detect a project's language and framework, then generate appropriate build/test/dev scripts for non-Node.js projects. The agent creates .iloom/package.iloom.json with shell commands tailored to the detected stack. Use this for Python, Rust, Ruby, Go, and other non-Node.js projects that don't have a…

iloom-ai/iloom-cli · 76 tokens

iloom-wave-verifier

Wave verification agent that checks must-have criteria from child issues after each swarm wave, invokes fix skills for failures, and reports structured results.\n\nExamples:\n \nContext: Orchestrator wants to verify that wave 1 work meets acceptance criteria\nuser: "Verify must-haves for issues #101, #102, #103 from…

iloom-ai/iloom-cli · 0 tokens

iloom-issue-phase-verifier

Use this agent after an implementation phase completes to independently verify that the phase's must-haves/invariants from the plan are actually met in the worktree. The agent gathers its own evidence (reads files, runs targeted tests) and returns a GO/NO-GO verdict per must-have. It reports violations but never fixes…

iloom-ai/iloom-cli · 308 tokens