Skill Claude CodeCodex
Safely create, review, apply, or repair tsumugi Drizzle migrations while protecting schema, SQL, snapshot, journal, and database-history consistency. Use for changes to apps/server/src/data/schema.ts or apps/server/drizzle, drizzle-kit generate/migrate operations, migration failures or no-op successes, journal…
Skill Claude CodeCodex
Collect and interpret read-only runtime evidence for tsumugi deterministic capture, Stop promotion, observation-first recall, legacy memory compatibility, continuity, archive, and scheduler paths. Use when monitoring production or staging health, comparing runtime trends, investigating deterministic backlog or…
Skill Claude CodeCodex
Select and run evidence-based verification for tsumugi changes across server, shared schemas, Admin UI, CLI, hooks, Drizzle migrations, and eval benches. Use when asked to test, verify, validate, review readiness, check a working tree or PR, confirm CI parity, or determine whether a tsumugi change is safe to commit…
Plugin Claude Code
Plugin marketplace listing 1 plugin: tsumugi.
Instructions file CodexOpenCode
A set of project instructions for developing tsumugi, including where code belongs, which existing utilities to reuse, and how its layers may depend on one another.
Instructions file
Claude Code instructions for archfill/tsumugi, a project described as: MCP-based memory layer for AI agents — observation, hybrid search, dreaming/synthesis.
Plugin Claude Code
tsumugi memory integration — 3 inject-only hooks (SessionStart, UserPromptSubmit, PreToolUse(Read)) that surface past memory and guide agent-driven saveobservation calls. Does NOT create observations from raw tool output (avoiding the contamination problem documented in ADR-011).
MCP server Claude CodeCodexCursor
MCP server "tsumugi", hosted remotely, as configured in archfill/tsumugi.
Hook
Runs when a session starts on startup, clear and compact, executing session_start.py via python3. From archfill/tsumugi.
Hook
Runs when you submit a prompt, before the agent sees it, executing user_prompt_submit.py via python3. From archfill/tsumugi.
Hook
Runs before the agent uses a tool for Read tool calls, executing pre_tool_use_read.py via python3. From archfill/tsumugi.
Hook
Runs after a tool call finishes for Bash tool calls, executing post_tool_use.py via python3. From archfill/tsumugi.
Hook
Runs when the agent finishes a response, executing stop.py via python3. From archfill/tsumugi.