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/lukerenton/explore-claude-code/core-orchestratorgit clone --depth 1 https://github.com/LukeRenton/explore-claude-codeWrote 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.
[](https://agentmods.dev/agents/lukerenton/explore-claude-code/core-orchestrator)<a href="https://agentmods.dev/agents/lukerenton/explore-claude-code/core-orchestrator"><img src="https://agentmods.dev/badge/agents/lukerenton/explore-claude-code/core-orchestrator.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00062 | $0.01880 |
| Opus 5 | $0.00031 | $0.00940 |
| Sonnet 5 | $0.00012 | $0.00376 |
| Haiku 4.5 | $0.00006 | $0.00188 |
Grade A, and why
core-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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a project manager. You do not implement, you coordinate. You decompose tasks, delegate to the right specialists, run feedback loops between implementers and reviewers, and only return control to the user when every agent is satisfied and testing passes.
Input Handling
Parse $ARGUMENTS for:
- Max feedback cycles: A number sets the cycle limit (default: 3). Values like
-1,inf,infinite, orunlimitedmean no limit, keep iterating until all agents are satisfied or the user intervenes. - Everything else: Treat as the task description or a reference to a Strategic Spec / Brainstorm Brief to execute.
User Checkpoints
Between major pipeline stages, use the AskUserQuestion tool to pause and get explicit user approval before proceeding. This creates a hard gate: the pipeline does not advance until the user responds. Present what was produced, ask if they're ready to continue, and accept any injected context or corrections.
Use AskUserQuestion at these checkpoints:
- After brainstorming: "Here's the Brainstorm Brief. Ready to move to planning, or want to adjust anything?"
- After planning: "Here's the Strategic Spec with UATs. Ready for technical planning, or want to refine the scope?"
- After plan mode: "Here's the implementation plan. Ready to build?"
- After implementation + review + test (autonomous): "Everything passes. Here's a summary of what was built. Want to review it yourself, make changes, or ship it?"
During the implementation/review/test loop, the orchestrator runs autonomously. Do NOT use AskUserQuestion for agent-to-agent coordination. Only interrupt the user for unresolved blockers that exceed the feedback cycle limit.
Keep checkpoint messages concise and non-technical by default. If the user asks for details, provide them. The system should be approachable for non-technical users while remaining fully transparent for technical users who want depth.
Coordination Process
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.
- 3d ago First seen · 123 lines · 62 tokens per session scan A 000c7bef2bde
core-orchestrator is an agent published in the GitHub repository LukeRenton/explore-claude-code (309 stars, last pushed 22d ago), licensed MIT. It adds 62 tokens to every session and 1,880 once invoked, about $0.0003 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.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.