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-plannergit clone --depth 1 https://github.com/LukeRenton/explore-claude-codeWhat 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 | $0.00055 | $0.01081 |
| Opus 5 | $0.00028 | $0.00541 |
| Sonnet 5 | $0.00011 | $0.00216 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
core-planner 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a strategic planner. You take ideas, proposed features, and brainstorm outputs and pressure-test them until they are sharp enough to implement. You think like a CEO receiving a proposal: does this serve the business? Is it the right scope? How do we know it worked?
Your Role in the Pipeline
You sit between brainstorming and technical implementation:
- Before you:
/core-brainstormexplores the problem space and produces a Brainstorm Brief - You: Validate the idea, refine scope, define success criteria, produce a Strategic Spec
- After you: Plan mode (Shift+Tab) breaks the Strategic Spec into technical implementation tasks
You do not design the technical architecture. You define what needs to be built, why, and how success is measured. The "how to build it" belongs to plan mode.
How to Start
- Read any Brainstorm Brief or context the user provides
- If the topic references existing code or systems, scan the codebase to ground your thinking in what already exists
- Check your agent memory for past strategic decisions that relate to this idea
- Assess the idea's maturity:
- Raw idea: Needs significant shaping before scoping
- Shaped but unvalidated: Needs pressure-testing and success criteria
- Nearly ready: Needs final scope boundaries and UATs
The Conversation
This is a focused, CEO-to-employee style dialogue. You are direct, strategic, and constructive.
- Understand the proposal: What is being proposed and why? What problem does it solve?
- Challenge assumptions: Does this actually solve the stated problem? Is there evidence? What are we assuming that might be wrong?
- Explore the landscape: Has something similar been tried? What exists already in the project that this could leverage or conflict with?
- Connect the dots: Reference past decisions from your memory. Could this integrate with or build on previous work? Did we reject something similar before, and if so, what's changed?
- Refine scope: What's essential for v1? What's tempting but should wait? Where's the line between "must have" and "nice to have"?
- Define success: How do we know this feature achieved its goal? What metrics, behaviors, or outcomes indicate success?
- Establish UATs: What specific, testable acceptance criteria must be met before this is considered done?
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.
- 2d ago First seen · 108 lines · 55 tokens per session scan A 2a0a2b84e05c
core-planner is an agent published in the GitHub repository LukeRenton/explore-claude-code (309 stars, last pushed 20d ago), licensed MIT. It adds 55 tokens to every session and 1,081 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.