orchestrateX

A set of routing rules for choosing among xdo, xdel, and xflow work modes. The modes control whether work is done directly, delegated through a parent-and-child task tree, or handled as a broader workflow.

In plain words
What is it for?
Use it to recommend or follow a mode for direct changes, delegated tasks, cross-module work, status checks, and other uncertain or high-impact requests.
Why use it?
It prevents ambiguous requests from being routed silently and keeps the chosen mode active until the work is complete. It also reserves parallel development for explicit requests.

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/treex-x/workflowx/orchestratex
Any agent
npx skills add TreeX-X/WorkFlowX --skill orchestratex
Clone the repo
git clone --depth 1 https://github.com/TreeX-X/WorkFlowX

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 688 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 $0.00022 $0.00688
Opus 5 $0.00011 $0.00344
Sonnet 5 $0.00004 $0.00138
Haiku 4.5 $0.00002 $0.00069

Measured 2d ago against content hash 8b7c0a716c52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrateX 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 2d 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/skills/orchestrateX/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

orchestrateX

Routing

Read the complete request and active context before selecting a mode.

  • Explicit xdo, xdel, xflow, or xstatus commands take precedence.
  • Without an explicit mode, recommend xflow for high-impact, cross-module, or uncertain work; recommend xdel for clear local work with an existing or requested Hybrid Tree; otherwise recommend xdo.
  • When the mode is ambiguous, present the three choices instead of silently selecting one.
  • Once a mode is active, keep subsequent messages in that mode until completion.
  • Parallel development is never implicit; activate it only when the user explicitly requests parallel work.

Modes

xdo - direct

  • Main Agent works directly using the requested skills.
  • Do not dispatch by default.
  • Parallel Agents are allowed only when the user explicitly requests parallel development.
  • Hybrid Tree and harness are optional.
  • Use engineeringX and perform self-review before reporting completion.

xdel - delegate

  • Use or create a Hybrid Tree Parent/Child.
  • Dispatch coderX once for the assigned Child.
  • coderX reads engineeringX and specX, then self-reviews.
  • Do not trigger evaluatorX or an iteration loop.

xflow - orchestrate

  • Run module 08 repository discovery, then load and run .claude/skills/socratesX/SKILL.md for only the unresolved decisions in the current analysis phase. Ask those questions in one batch, offer options only for real trade-offs, and use one confirmed Ready Summary gate before creating or updating the Hybrid Tree.
  • Execute Children in dependency order.
  • Dispatch coderX once per Child with engineeringX and specX.
  • Trigger evaluatorX after each Child.
  • After evaluation, the Main Agent classifies findings:
    • local implementation defect: re-dispatch the same Child once with a minimal repair packet;
    • cross-Child integration issue: compress it into an integration note for the affected later Child;
    • architecture or scope issue: the Main Agent updates the plan or fixes it directly.
  • A Child gets at most one automatic repair re-dispatch by default. Further repair requires a Main Agent decision.
  • Do not pass complete prior Child context to later Children; pass only relevant contracts, files, failures, and risks.

Read the full file on GitHub · 61 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 61 lines · 22 tokens per session scan A 8b7c0a716c52

Subscribe to this mod's changes

orchestrateX is a skill published in the GitHub repository TreeX-X/WorkFlowX (55 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 688 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.