Tsubasa banner
ramarahmanda ramarahmanda

Tsubasa

AI community

Description

Your engineering captain: a repo-resident AI persona with a knowledge graph stored in git. Agents cite incidents, ADRs and PRs instead of guessing — 47% fewer wrong answers, 40% cheaper on a public benchmark. Claude Code plugin + CLI.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

the tsubasa captain

tsubasa

**Your engineering captain.** He knows your code, your outages, your history, and your roadmap. He ships you past storms.

[![Stars](https://img.shields.io/github/stars/ramarahmanda/tsubasa?style=flat)](https://github.com/ramarahmanda/tsubasa) [![PyPI](https://img.shields.io/pypi/v/tsubasa)](https://pypi.org/project/tsubasa/) ![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue) ![Claude Code plugin](https://img.shields.io/badge/claude--code-plugin-orange) ![License: MIT](https://img.shields.io/badge/license-MIT-blue)

**47% fewer wrong answers · 45% cheaper · 24% faster**

you:         why does payment-svc cap its pool at 40?

no captain:  pool.go sets it to 40. Likely to avoid exhausting database
             connections — a common pattern. You could raise it if your
             database handles more concurrent connections, though you may
             want to load-test first and monitor p99 during the rollout.

captain:     The July 3 flash-sale incident: pool exhaustion took p99 to 8s.
             adr-payments-pool-sizing fixed the cap because RDS connections
             were the real limit. PR-1841, services/payment/pool.go:88.

             goal-replace-apigee retires the layer in front of this service.
             Don't invest in the current routing.

Numbers

The measurement is a real agent doing real work: a headless Claude Code session answering questions about four pinned public repos — cloudnative-pg, etcd, kubernetes/enhancements, postgres — scored on what it cites. 72 questions, the same agent with and without a captain, 144 runs, Claude Sonnet 5 in both arms and as the judge.

each metric as a percent of the no-captain baseline
vs no-captain baseline wrong answers cost time tool calls
captain −47% −40% −24% −49%

| per quest