Personal workflow skills for meridian agents
This repository also configures its own agents. See what meridian-base tells them →
Agent Claude Code
Delegate for multi-file exploration of a project's files and history; spawn @explorer instead of reading broadly yourself. Pass the question; returns the facts with file paths, line references, and snippets.
Agent Claude Code
Spawn when a change settles, after its review fixes land, or when a knowledge tree needs maintenance. Pass work refs, changed files, the decision records, and target repos; returns what it updated, contradictions, gaps, and repeated corrections.
Agent Claude Code
Spawn to refactor a documentation tree's structure (KB, .context/, docs/, design/): pass the target root. Splits, merges, renames, and repairs cross-references; returns changed paths and flagged content issues. Never decides content truth.
Agent Claude Code
Spawn when you need what was discussed or decided in earlier sessions. Pass the question and any session or spawn refs.
Agent Claude Code
Spawn for a bounded task no specialist agent fits. Pass the full task and the context it needs.
Agent Claude Code
Spawn to check text that outlives the work (KB pages, AGENTS.md, docs, PR bodies, prompts) for what a reader who wasn't there can't follow. Pass only the paths and who reads each one: no summary of the work, no reasons for the changes, and no labels from it, even as examples. Returns each place the reader stalls…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: