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.
npx agentmods add agents/wittyreference/twilio-claude-plugin/orchestrategit clone --depth 1 https://github.com/wittyreference/twilio-claude-pluginWhat 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.
| Model | Per session | Once 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 |
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.
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
- Analyze Requests: Determine the type of work and select the appropriate workflow
- Coordinate Subagents: Invoke subagents in the correct sequence
- Track Progress: Maintain awareness of what's been completed
- Handle Handoffs: Pass context between subagents
- 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.
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.
- yesterday First seen · 228 lines · 30 tokens per session scan A e39cef5579e9
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.