Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Agent Orchestration Rules

A short rule set that tells Claude to delegate implementation work to sub-agents so the main conversation keeps its context.

Dev & CodingIntermediate★ 3,932⑂ 298AI score 7/10Last updated: Jan 26, 2026

What it does

  • Steers Claude to spawn an implementation sub-agent whenever you ask it to build, implement, or execute a plan phase, instead of reading files in the main chat.
  • Contrasts the wasteful pattern (read → understand → edit → report in main context, 2000+ tokens) with the efficient one (delegate, receive a ~200-token summary).
  • Ships a decision table: use agents for multi-file work, plan phases, and features with tests; skip them for one-line fixes or quick config tweaks.
  • Gives a template for the hand-off prompt: plan location, list of artifacts to create, and a request for a completion summary.

Who it's for

  • Developers who run long Claude Code sessions and hit context exhaustion.
  • Teams that write plan documents first and implement them phase by phase.
  • Anyone regularly handing multi-file feature work to an AI coding agent.

Examples

  1. "Implement Phase 4 of the Artifact Index plan" → the agent locates the plan, creates the hook, wrapper, script, registers settings.json, then reports a summary.
  2. "Build this feature with tests" → the agent explores the codebase, writes code, and runs the test suite in its own context.
  3. "Fix this typo" → per the table, no agent is spawned; the edit happens directly.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/parcadei/Continuous-Claude-v3/HEAD/.claude/skills/agent-orchestration/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the .claude/skills/agent-orchestration folder from the GitHub repo parcadei/Continuous-Claude-v3 into my ~/.claude/skills/agent-orchestration/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/parcadei/Continuous-Claude-v3.git && mkdir -p ~/.claude/skills && cp -r Continuous-Claude-v3/.claude/skills/agent-orchestration ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal in your working directory.
  2. Clone the repository: git clone https://github.com/parcadei/Continuous-Claude-v3.git
  3. Create the skills folder if needed: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r Continuous-Claude-v3/.claude/skills/agent-orchestration ~/.claude/skills/
  5. Verify that ~/.claude/skills/agent-orchestration/SKILL.md exists.
  6. Restart Claude Code. The skill is marked user-invocable: false, so it is consulted automatically on implementation requests rather than called by name.
  7. The thoughts/shared/plans/ path in the sample prompt is this repo's convention — swap in your own plan-document path.
View source on GitHub ↗License: MIT