meridian-base

Use when grilling should be grounded primarily in project artifacts. Loads `/grill`, checks project vocabulary and prior decisions first, and spawns bounded explorers when the answer should come from docs.

Load for large human-facing outputs: reports, docs, multi-section explanations, artifacts. Choose the right form for each beat (prose, diagram, table, mockup) and put the answer first, depth behind it. If the medium allows, use progressive disclosure.

Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.

Anchor work in a work item: artifacts on disk, not in context.

Investigate and engage concurrently: don't block on evidence before surfacing your read.

Use when exploring or changing the codebase: read AGENTS.md first, use .context/CONTEXT.md for detail, keep intent docs succinct.

Use when recovering decisions or context from conversation history: session log navigation, transcript delegation.

Use when establishing shared vocabulary: resolve terminology early, one name per concept, vocab files as record.

Use when a workspace has changes from other agents: safe orientation, preserving unfamiliar files.

Use when orienting in an unfamiliar area: fans out parallel explorers across code, knowledge, and history, then synthesizes one orientation map.

End this session and produce a launch command for the user's next interactive primary.

Use when validating markdown links or Mermaid diagrams.

Use when a spawn fails due to sandbox or permission restrictions.

Load when building a static HTML artifact: single page or multi-page site to make structured information explorable through layout and navigation.

Load before writing or revising human-facing text. Choose words deliberately, ground the piece in the reader's context, and remove default LLM phrasing before the final draft.

Load when turning intent into an executable goal for an agent, spawn, work item, experiment, or handoff. Use to define outcome, evidence, constraints, anti-goals, stop conditions, and reporting shape before work begins.

Use when grilling should be grounded in evidence. Loads `/grill`, then checks the plan, terms, and assumptions against project artifacts first and primary sources when needed.

Use in conversation to stress-test a plan or direction. Interviews the human branch by branch, sharpens terminology, challenges assumptions, and asks the next high-leverage question with a recommended answer.

Use before acting on human instructions: separate what they said from what they meant.

User-invoked pause before reporting to check intent vs literal completion, surface adjacent wins, and route knowledge capture.