record-knowledgelisted

# Record Knowledge ## Goal Capture tacit knowledge discovered during work and make it available for future sessions. ## When to Reference - **New session start**: Search `.claude/knowledge/entries/` for active entries related to the current task before starting work - If an `overview` entry exists for the topic, read it first — load `detail` entries on demand to save context - **Progress update**: Check if related entries need updating based on new discoveries - Not needed when resuming a session (context is already preserved) ## Execution Delegate the recording work to a subagent to minimize main context consumption. 1. Analyze the user input or work context and prepare structured input fields 2. Determine the knowledge base path (default: `.claude/knowledge/entries/`) 3. Spawn a subagent with the following configuration: ``` Agent( subagent_type: "general-purpose", description: "record knowledge entry", prompt: | You are a knowledge recording agent. Read the procedure file and follow it precisely. ## Input ### what（事実） {what} ### why（判断理由） {why} ### context（背景情報） {context} ### tags_hint（推奨タグ） {tags_hint} ## Instructions 1. Read the procedure file at: {plugin_root}/skills/record-knowledge/procedure.md 2. Follow the procedure step by step 3. The knowledge base is at: {project_root}/.claude/knowledge/ 4. Return: filename, # heading, ## headings, and linked entries ) ``` Replace the placeholders: -