Provider-neutral agent kit + local artifact-memory substrate (MCP server, generators, guards, Qdrant-backed semantic search over a personal workspace)
Command Claude Code
Promote a durable agent-memory lesson to the right tier — repo wiki Field Notes (gated), repo CLAUDE.md, or data/references — without duplicating it across tiers. Use when a pipeline agent captured a significant, durable lesson in .claude/agent-memory/ /lessons.md that is useful beyond that one agent/run, or when the…
Command Claude Code
Run the canonical delivery-state v2 milestone pipeline (Research → Implement → independent adversarial review → Rectify/closure → Publish → Apply → Verify). Use for a non-trivial fixed milestone id when code/checklist completion must be distinguished from live operational delivery.
Command Claude Code
Build a structured technical roadmap (Goal → Epics → Now/Next/Later milestones → Stories) from a problem statement or the current conversation. Use when the user invokes /roadmap , says "plan this project", "build a roadmap for", "decompose this into milestones", "what's the path to ship X", or has been discussing a…
Command Claude Code needs its repo
Convert an existing skill at data/skills/ /SKILL.md into a slash-command + N-subagent + agent-memory pattern. Use when a skill has grown into a multi-phase orchestrator (e.g. has "Phase 1 / Phase 2 / Phase 3 / Phase 4" structure, dispatches sub-tasks, holds state across phases) and you want to refactor it to match the…
Command Claude Code
Run a 4-phase spike pipeline (Design → Execute → Write-up → Review) that answers exactly one assumption with a YES / NO / UNCERTAIN verdict DERIVED from measured data. State is a machine phase-machine (spike-checkpoint.py), artifacts are typed + validated (spike-validate.py), and the verdict is computed, not authored…
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: