Coordinate nontrivial work in the ctx repository when a task has independent investigation, implementation, or test lanes; compute-heavy checks; or repetitive changes suited to scripts or codemods. Use for decomposition and concurrency decisions, not simple edits or questions.
Scanned 9/5/2026
Install to Claude Code
npx -y skills add stevesolun/ctx --skill ctx-dispatch --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ctx Dispatch?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/stevesolun-ctx-dispatch)More formats (shields.io, HTML) on the badges page.
---
name: ctx-dispatch
description: Coordinate nontrivial work in the ctx repository when a task has independent investigation, implementation, or test lanes; compute-heavy checks; or repetitive changes suited to scripts or codemods. Use for decomposition and concurrency decisions, not simple edits or questions.
---
# Dispatch ctx work
1. Identify the requested outcome, dependencies, and independently executable
lanes. Keep simple work local.
2. Reserve subagents for bounded semantic work that benefits from isolated
context.
3. Run lanes concurrently only when this reduces elapsed time without duplicate
work or competing writes. Give each writer disjoint ownership; keep shared
files with one owner.
4. Inspect CPU, memory, and disk pressure only before genuinely compute-heavy
work, then size concurrency to the available capacity.
5. Keep scope, dependency resolution, and synthesis with one coordinator. Merge
evidence from every required lane before reporting completion.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...