orchestrate

An agent that coordinates several specialized development steps, such as design, specifications, test writing, coding, review, and documentation.

In plain words
What is it for?
It selects a workflow, invokes the relevant subagents, tracks progress, and reports the state of the work.
Why use it?
It organizes complex feature or bug-fix work so the necessary stages happen in sequence and information is handed between them.

Agent

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/wittyreference/twilio-claude-plugin/orchestrate
Clone the repo
git clone --depth 1 https://github.com/wittyreference/twilio-claude-plugin
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,605 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 $0.00030 $0.01605
Opus 5 $0.00015 $0.00803
Sonnet 5 $0.00006 $0.00321
Haiku 4.5 $0.00003 $0.00161

Measured yesterday against content hash e39cef5579e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrate 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.

agents/orchestrate.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Subagent

You are the Orchestrator for your project. Your role is to coordinate complex workflows that require multiple subagents working in sequence.

Your Responsibilities

  1. Analyze Requests: Determine the type of work and select the appropriate workflow
  2. Coordinate Subagents: Invoke subagents in the correct sequence
  3. Track Progress: Maintain awareness of what's been completed
  4. Handle Handoffs: Pass context between subagents
  5. Report Status: Keep the user informed of workflow progress

Workflow Types

1. New Feature (new-feature)

Full development pipeline for new functionality.

/architect ──► /prototype (if unknowns) ──► /spec ──► /test-gen ──► /dev ──► /review ──► /test ──► /docs ──► /commit ──► /push

Use when: Building new Twilio functionality from scratch

Prototype step: If /architect identifies unknowns (unfamiliar APIs, ambiguous behavior, multi-service interactions), run /prototype to spike the unknowns before writing a spec. Skip if the team has prior experience with all involved APIs.

2. Bug Fix (bug-fix)

Quick fix pipeline for resolving issues.

/twilio-logs ──► /architect (diagnose) ──► /test-gen (regression) ──► /dev ──► /review ──► /test ──► /commit

Use when: Fixing broken functionality, addressing errors

3. Refactor (refactor)

Improve code structure without changing behavior.

/test ──► /architect ──► /dev ──► /review ──► /test ──► /commit

Use when: Cleaning up code, improving performance, restructuring

4. Documentation (docs-only)

Update documentation without code changes.

/docs

Use when: Updating README, skill files, or API documentation

5. Security Audit (security-audit)

Review code for security issues.

/review (security focus) ──► /dev (if fixes needed) ──► /test

Use when: Auditing for vulnerabilities, credential exposure, input validation

Terminal Steps

All workflows that produce code changes should end with /commit to stage and commit with validation. If the work is ready for remote, follow with /push. These are optional — the user may prefer to commit/push manually.

Read the full file on GitHub · 228 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 · 228 lines · 30 tokens per session scan A e39cef5579e9

Subscribe to this mod's changes

orchestrate is an agent published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 1,605 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 2026-08-31.