captain-onboard

captain-onboard is a skill for Claude Code from ramarahmanda/tsubasa. It costs 110 tokens per session (1,399 once invoked), scanned A, original, MIT.

A setup skill for creating or updating a “captain,” an assistant that keeps shared knowledge about a code repository or workspace. It uses the `tsubasa` command-line tool to gather sources such as Git repositories and architecture documents.

In plain words
What is it for?
Use it to create a captain, ask a few setup questions, find relevant project knowledge, and run the initial knowledge import; use it to upgrade an existing captain after updating `tsubasa`.
Why use it?
It reduces the need to repeatedly explain the project’s structure, decisions, and background to the coding agent. It also provides a defined upgrade path when an existing captain was created by an older version of the tool.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the tsubasa plugin — 5 skills, 4 hooks shipped together

Good fit Use it to create a captain, ask a few setup questions, find relevant project knowledge, and run the initial knowledge import; use it to upgrade an existing captain after updating tsubasa.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ramarahmanda/tsubasa/onboard
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ramarahmanda/tsubasa --skill onboard
Clone the repo
git clone --depth 1 https://github.com/ramarahmanda/tsubasa

Made for: Claude Code.

Or install tsubasa, the plugin that ships this one along with the rest of its 5 skills, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for captain-onboard

README.md
[![agentmods](https://agentmods.dev/badge/skills/ramarahmanda/tsubasa/onboard/github.svg)](https://agentmods.dev/skills/ramarahmanda/tsubasa/onboard)
Your own site
<a href="https://agentmods.dev/skills/ramarahmanda/tsubasa/onboard"><img src="https://agentmods.dev/badge/skills/ramarahmanda/tsubasa/onboard/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for captain-onboard

Your own site · 80×15
<a href="https://agentmods.dev/skills/ramarahmanda/tsubasa/onboard"><img src="https://agentmods.dev/badge/skills/ramarahmanda/tsubasa/onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.01399
Opus 5 $0.00055 $0.00700
Sonnet 5 $0.00022 $0.00280
Haiku 4.5 $0.00011 $0.00140

Measured 9d ago against content hash d02d1629118c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

captain-onboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/onboard/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Captain onboard

Birth a captain in this repo or workspace. Everything through conversation — the user never touches the CLI.

Already a captain here?

If .tsubasa/captain.toml exists, this repo has a captain and init will refuse. Run tsubasa upgrade instead: it is idempotent and brings a captain built by an older tsubasa up to date (schema stamp, source graph, memory tiers), reporting every change. Then stop, and report what changed. Only run the steps below when there is no captain here.

Steps

  1. CLI present? which tsubasa — if missing: uv tool install tsubasa (fallback: uv tool install git+https://github.com/ramarahmanda/tsubasa). If uv is missing too, ask before installing it.
  2. One round of questions (single message, not an interview):
    • captain name (suggest one from the repo/org name, e.g. captain-)
    • role (default: Engineering Director)
    • domains (suggest 3-5 from what you see in the codebase)
  3. Auto-detect sources — scan for:
    • git repos: .git here or in first-level subdirectories (workspace mode)
    • ADR/design/architecture docs: docs/adr, docs/decisions, */docs/*.md (design docs are usually the highest-value source — do not skip them)
    • postmortems/incidents: dirs or files matching incident/postmortem/outage Present the proposed source list as a table and confirm in one line. NEVER add credential files, .env, or secret stores as sources.
  4. Scaffold: tsubasa init <name> --role "<role>" --domains <d1,d2>, then register every confirmed source with tsubasa source add <adapter> <path> [--glob "<glob>"]. NEVER hand-edit captain.toml — the command validates and keeps it parseable.
  5. Persona check. init generates .tsubasa/persona.md and includes it from CLAUDE.md alongside the hot-memory include: response rules (straight answers, cite or "I don't know", never an id you did not read, the recorded value first, push back on ADR conflicts), the enforced ADR format, and communication rules per Strunk & White's The Elements of Style ("omit needless words"). Read it, verify both include lines are present, do NOT duplicate the rules anywhere, and tell the user in one line that persona.md is generated (tsubasa rewrites it on upgrade) and their own additions go in CLAUDE.md around the include. From this step on, ANSWER IN THAT STYLE — the onboarding report itself is the first demonstration of the persona.
  6. First ingest: tsubasa ingest (deterministic: docs, tags, ADR-marked commits).
  7. Code index — always, not optional. tsubasa index: deterministic code-only graphify indexes per workspace repo (local AST, no LLM, seconds per repo; non-code files excluded by design). Then tsubasa link to seed anchors between graph entities and code nodes. This is what lets queries join the why (native graph) to the what-is (code graph). Optional depth, on request only: /graphify ./<repo> --mode deep for semantic code edges on a repo that warrants it — never a default; docs enter the graph via tsubasa sources, not graphify.
  8. Study phase — this is what makes the captain a veteran. Deterministic ingest is thin on repos without ADR conventions; now read and distill:
    • each detected docs file: extract the decisions/architecture it records
    • full git history: run tsubasa study (headless, chunked — distills EVERY commit into events; --max-chunks N bounds cost). Then tsubasa resolve (merge duplicate entities) and tsubasa profile (rich profiles for hub entities). This is the 25-year-veteran pass.
    • architecture scan per repo: README, docker-compose / k8s manifests / helm values, CI/CD configs, IaC — distill entities for services, envs, and secret-REFS (name + where it lives, NEVER the value) and relations (depends_on, deployed_to, built_by, reads_secret). Do NOT study application source code: structure is answered live from code (it goes stale silently in a graph); code-level insight enters the graph organically via recall's learn-on-miss. Persist each distilled finding as one event with entities/relations: tsubasa event add --type <decision|note|incident> --title "..." \ --summary "..." --impact <i> --domains <d> --ref <commit|doc>:<id> \ --entity <id>:<type>:<name>:<desc> --relation <src>:<pred>:<tgt> Aim for quality over volume: 15-30 well-connected events beat 200 thin ones.
  9. Report in captain style (per the step-5 principles): events per source, what the study phase learned (one line per theme), entity count, indexed repos + anchor count, hot-tier size, and 2-3 example questions the user can now ask ("try: why …").
  10. If this is a git repo, note that .tsubasa/ + CLAUDE.md are commit-ready (do not commit unasked). In a multi-repo workspace root, note the knowledge lives at the workspace level.

Read the full file on GitHub · 85 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 85 lines · 110 tokens per session scan A d02d1629118c

Subscribe to this mod's changes

captain-onboard is a skill published in the GitHub repository ramarahmanda/tsubasa (8 stars, last pushed 12d ago), licensed MIT. It adds 110 tokens to every session and 1,399 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

decision

Single entry point for all decision operations: capture, search, manage. Routes based on natural language intent.

zimalabs/code-decisions · 23 tokens

repo-standard

Use when working in a RepoKit-compliant repo — about to commit or open a PR, adding a learning / ADR, or asking "where does X go" or "what's the convention here". Loads the RepoKit conventions and the pre-commit / pre-PR checklists.

PBNZ/repo-kit · 61 tokens

tree-ring-memory

Guides AI agents in using Tree Ring Memory for durable recall, project decisions, user preferences, warnings, future seeds, privacy-safe memory capture, and lifecycle-aware forgetting.

TerminallyLazy/tree-ring-memory-claude-plugin · 38 tokens

openlore-brainstorm

Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.

clay-good/OpenLore · 40 tokens

mission-brief

Mission-driven SDD orchestrator: take a feature description, structure it into a Mission Brief (goal, constraints, success criteria), generate an ordered step list with prompts that trigger installed SDD skills via model invocation or command-file discovery, and walk those steps to converged implementation. Use when…

tikalk/adlc-team-skills · 99 tokens

levelup-publish

Compile accepted Context Directive Records (CDRs) into team-ai-directives artifacts and create a draft PR. Builds context modules, evals goldensets, and/or skills based on CDR context types.

tikalk/adlc-team-skills · 46 tokens