archfill/tsumugi
MCP-based memory layer for AI agents — observation, hybrid search, dreaming/synthesis
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~4.0k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code
$ npx degit archfill/tsumugi/.claude ./rig-tsumugi # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit archfill/tsumugi/.agents/skills/drizzle-migrate-safety .claude/skills/drizzle-migrate-safety $ npx degit archfill/tsumugi/.agents/skills/tsumugi-runtime-observe .claude/skills/tsumugi-runtime-observe $ npx degit archfill/tsumugi/.agents/skills/tsumugi-verify .claude/skills/tsumugi-verify
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| tsumugi | local / custom · remote | 2.5k |
Skills (3)
Similar rigs
Shibata-1273352/BuiltwithClaudeJapan2026
撮るだけで、目の前の日本が、意味と物語になる。Photo in, meaning and verified history out: Claude reads, code decides.
Minimalist 1.2k tok · · Q15
anomalyco/opencode
The open source coding agent.
Pragmatist 14.3k tok · · Q8
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok · · Q0
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
Pragmatist 4.2k tok · · Q18