llm-council

When to use

• 

  When you need to set up llm council reliably

• 

  When you need to debug llm council operations

• 

  When you need a safer llm council deployment flow

How to use

1. 1

   Share load the task spec, and explore the codebase you are in to get a strong sense of the product

2. 2

   Share always ask thorough intake questions to build a clear task brief. Clarify any ambiguities, constraints, and success criteria. Remind the user that answers are optional but improve plan quality

3. 3

   Share build planner prompts and launch the configured planner agents in parallel background shells

4. 4

   Collect outputs, validate Markdown structure, and retry up to 2 times on failure. If any agents fails, yield and alert the user to fix the issue

5. 5

   Share anonymize plan contents and randomize order before judging

Example conversation

case

You

We you need to set up llm council reliably. Can you give a concrete plan and how to verify the outcome?

Agent

The agent applies the llm council workflow to your current context. You get prioritized next actions, a checklist for validation. It also states what to measure after changes so you can confirm impact.

FAQ

Q：How do I use this for a llm council task?

Q：What should I prepare before starting llm council work?

Q：What do I receive after a llm council request?

Q：What llm council tasks are out of scope here?