Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From greymatter
Coordinates chunk execution when the user works directly (no subagent). Reads chunk files and observations, emits code changes, and transitions to completing-chunks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/greymatter:executing-chunksThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read `prompts/executing-chunks/prompt.md` and follow it. The work is identical whether prime is executing inline or a subagent is dispatched — the prompt is the single source of truth.
Read prompts/executing-chunks/prompt.md and follow it. The work is identical whether prime is executing inline or a subagent is dispatched — the prompt is the single source of truth.
When done: offer completing-chunks and stop. Do not commit, do not restart services (those are session-wide rules from CLAUDE.md/brain).
npx claudepluginhub advenire-consulting/greymatter --plugin greymatterWrites the next chunk's assignment file with auto-injected drift preamble, preparing it for an executing-chunks subagent. Useful for chunk-based development pipelines.
Executes written implementation plans in batched sessions: loads plans, identifies runnable tasks via hive_status, delegates to workers, reports for review, and runs hygienic code reviews between batches. Use for separate execution sessions with checkpoints.
Use when executing implementation plans with independent tasks in the current session