orchestrator

orchestrator is a skill for Claude Code, Codex from Sistema2D/FrameCode-VibeWork. It costs 15 tokens per session (575 once invoked), scanned A, original, Apache-2.0.

A procedure for coordinating complex work across separate areas such as security, design, performance, refactoring, testing, documentation, and release tasks.

In plain words
What is it for?
Use it when a plan has multiple domains, needs parallel work, or carries substantial risk. If delegation tools are unavailable, it organizes the work into sequential task blocks.
Why use it?
It prevents overlapping edits and made-up tools when work is delegated. It also keeps the main agent responsible for review, validation, and closing the plan.

Skill for Claude CodeCodex

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 skills/sistema2d/framecode-vibework/orchestrator
Any agent
npx skills add Sistema2D/FrameCode-VibeWork --skill orchestrator
Clone the repo
git clone --depth 1 https://github.com/Sistema2D/FrameCode-VibeWork

Made for: Claude Code, Codex.

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/skills/sistema2d/framecode-vibework/orchestrator.svg)](https://agentmods.dev/skills/sistema2d/framecode-vibework/orchestrator)
Your own site
<a href="https://agentmods.dev/skills/sistema2d/framecode-vibework/orchestrator"><img src="https://agentmods.dev/badge/skills/sistema2d/framecode-vibework/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 575 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 $0.00015 $0.00575
Opus 5 $0.00008 $0.00287
Sonnet 5 $0.00003 $0.00115
Haiku 4.5 $0.00002 $0.00057

Measured 4d ago against content hash 591a6c2fcee0, 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 4d 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.

FCVW/skills/orchestrator/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SKILL: Orchestrator

Purpose

Coordinate complex plans without pretending unavailable tools exist. The orchestrator is functional in two modes:

  • Delegated mode: use subagent tools only when the current environment explicitly provides them.
  • Sequential mode: if no subagent tool exists, split the work into bounded task blocks and execute them one at a time under the active plan.

Activation Triggers

Load this skill when a plan spans multiple domains, has R3+ risk, mentions parallel work, or requires coordination between security, UX, performance, refactoring, docs, tests, and release.

Inputs

Active plan, ownership boundaries, dependency graph, available execution capabilities, work-package files, validation commands, and the authority granted for delegation.

Hard Rules

  • Do not invent tool names such as invoke_subagent if the environment does not expose them.
  • Do not open parallel edits against the same soft-locked files.
  • Every delegated or sequential task must cite the active plan and affected files.
  • Domain agents must load their own SKILL.md before acting.
  • The main agent remains responsible for review, validation, changelog, and plan closure.

Workflow

  1. Read the active plan and identify independent work packages.
  2. Check Plans/in_progress/ for scope collisions.
  3. Select execution mode:
    • delegated mode when subagent tools are available;
    • sequential mode otherwise.
  4. For each work package, define:
    • exact files in scope;
    • required skill;
    • behavior to preserve;
    • validation evidence;
    • rollback note.
  5. Execute or delegate the smallest safe package first.
  6. Review each result against the plan acceptance criteria.
  7. Do not close the plan until all packages are validated or explicitly deferred.

Output Required

Add this block to the active plan:

## Orchestration

- Skill loaded: `skills/orchestrator/SKILL.md`
- Execution mode: `delegated` / `sequential`
- Work packages:
  - `<package>`: `<skill>`, `<files>`, `<validation>`
- Collision check:
- Deferred packages:

Read the full file on GitHub · 75 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. 4d ago First seen · 75 lines · 15 tokens per session scan A 591a6c2fcee0

Subscribe to this mod's changes

orchestrator is a skill published in the GitHub repository Sistema2D/FrameCode-VibeWork (23 stars, last pushed 4d ago), licensed Apache-2.0. It adds 15 tokens to every session and 575 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 2026-08-30.