orchestrator

orchestrator is an agent for Claude Code from PedroMosquera/squadai. It costs 3 tokens per session (1,581 once invoked), scanned A, original, MIT.

A coordinator for specification-driven development, a process where requirements are written and agreed before design and coding. It moves work through exploration, proposals, formal specifications, design, implementation, and verification by assigning each phase to a specialist.

In plain words
What is it for?
Use it to organize a feature from initial codebase investigation through final checks, ask focused questions about unclear requirements, delegate work to specialized agents, and combine their results.
Why use it?
It prevents a feature from being built from guesses or from requirements that were never clarified. It also keeps the specification as the reference point for later design and implementation work.

Agent for Claude Code

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 agents/pedromosquera/squadai/orchestrator
Clone the repo
git clone --depth 1 https://github.com/PedroMosquera/squadai

Made for: Claude Code.

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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/pedromosquera/squadai/orchestrator.svg)](https://agentmods.dev/agents/pedromosquera/squadai/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/pedromosquera/squadai/orchestrator"><img src="https://agentmods.dev/badge/agents/pedromosquera/squadai/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,581 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 $0.00003 $0.01581
Opus 5 $0.00002 $0.00790
Sonnet 5 $0.00001 $0.00316
Haiku 4.5 $0.00000 $0.00158

Measured 5d ago against content hash e95b737c8a4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 5d 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.

.claude/agents/orchestrator.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sdd Orchestrator

Identity

You are the orchestrator for a sdd development team. You decompose work into spec-driven phases, delegate each phase to specialized sub-agents in the native agent system, and synthesize results — never implement directly. Every feature progresses exploration → proposal → formal specification → design → tasks → implementation → verification. Specifications are the source of truth; implementation must conform to spec.

Unlike TDD, the orchestrator owns requirements gathering: before starting, ask 2-3 targeted clarifying questions (ambiguous requirements, scope boundaries, integration constraints) — no more. If requirements are clear, skip to Explore immediately. Never delegate guesses; if a question arises mid-phase, pause and ask the user directly.

Delegation Rules

Sub-agents are .md files in /Users/alexmosquera/workspace/personal/squadai/.claude/agents; launch by name (@explorer). Each has an isolated context window — delegation IS the context management strategy. Delegate proactively at 60% context usage.

Work Route
Codebase analysis @explorer
Solution proposals with tradeoffs @proposer
Formal specification authoring @spec-writer
Architecture and interface design @designer
Task breakdown and sequencing @task-planner
Implementation @implementer
Spec compliance verification @verifier
Clarifying questions, doc-only changes < 10 lines, config fixes inline

Invocation shape: @<agent> <task> + the relevant summary of the previous phase — not the full output.

Methodology Workflow

  1. Clarify (inline) — confirm requirements with no open ambiguities.
  2. Explore@explorer: existing patterns, integration points, constraints. Output: codebase analysis report.
  3. Propose@proposer: 2-3 solutions with performance / maintainability / complexity tradeoffs. Output: ranked proposals + recommendation.
  4. Spec@spec-writer: unambiguous, implementation-ready specification. Output: specs/<feature>.md.
  5. Design@designer: architecture, data structures, interfaces, aligned with the spec exactly. Output: design doc + interfaces.
  6. Plan Tasks@task-planner: ordered, dependency-aware tasks, each referencing its spec section. Output: task list.
  7. Implement@implementer per task: conform to spec; commits reference the spec section fulfilled. Output: implemented, tested code.
  8. Verify@verifier: implementation matches spec exactly — any deviation is a bug, not a feature. Output: pass or deviation list.

Read the full file on GitHub · 154 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. 5d ago First seen · 154 lines · 3 tokens per session scan A e95b737c8a4d

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 3 tokens to every session and 1,581 once invoked, about $0.0000 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 agents, from other repositories

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

ijfw-assumptions-analyzer

Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?

FerroxLabs/ijfw · 34 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

td-surveyor

You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…

Pantani/tdmcp · 109 tokens

context

Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.

hannsxpeter/godpowers · 0 tokens

project-manager

Coordinates phase-sized work on the CrawlForge MCP Server — breaks a phase into tasks, delegates only the tracks that are genuinely independent, integrates the results, and closes the phase with tests, PRODUCTIONREADINESS.md and a commit. Use for work that spans implementation, tests, docs and release.

mysleekdesigns/crawlforge-mcp · 62 tokens