shipyard-map

shipyard-map is a skill for Claude Code, Codex from lgbarn/shipyard. It costs 88 tokens per session (468 once invoked), scanned A, original, MIT.

A read-only codebase-mapping tool for understanding an existing project. It documents the technology stack, architecture, testing and coding conventions, and areas of risk.

In plain words
What is it for?
Use it when onboarding to a repository, documenting a project, or investigating legacy code. It produces files such as STACK.md, ARCHITECTURE.md, TESTING.md, CONVENTIONS.md, and CONCERNS.md without modifying code.
Why use it?
It gives a developer an overview of an unfamiliar or inherited codebase before they make changes. It highlights how the system is organized as well as fragile, outdated, or security-sensitive parts.

Skill for Claude CodeCodex

Part of the shipyard plugin — 25 skills, 25 commands, 20 agents, 6 hooks shipped together

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.

agentmods
npx agentmods add skills/lgbarn/shipyard/shipyard-map
Any agent
npx skills add lgbarn/shipyard --skill shipyard-map
Clone the repo
git clone --depth 1 https://github.com/lgbarn/shipyard

Made for: Claude Code, Codex.

Or install shipyard, the plugin that ships this one along with the rest of its 25 skills, 25 commands, 20 agents, 6 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 shipyard-map

README.md
[![agentmods](https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-map.svg)](https://agentmods.dev/skills/lgbarn/shipyard/shipyard-map)
Your own site
<a href="https://agentmods.dev/skills/lgbarn/shipyard/shipyard-map"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-map.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 468 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00088 $0.00468
Opus 5 $0.00044 $0.00234
Sonnet 5 $0.00018 $0.00094
Haiku 4.5 $0.00009 $0.00047

Measured 5d ago against content hash 3e60c591db08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipyard-map 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 5d 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.

codex/skills-extra/shipyard-map/SKILL.md · 35 lines

What it actually says

Mapping a codebase (Codex inline-sequential)

This is the mapper role from Shipyard's /shipyard:init and /shipyard:map flows, adapted for Codex. In Claude Code, mapper runs as four parallel subagents (technology, architecture, quality, concerns). Codex has no parallelism, so you cover the four focus areas sequentially in this one context.

You are an analysis-only role. You MUST NOT modify any code — you read, analyze, and document. Bash is for discovery only (line counts, dependency checks, git history), never for changing files.

Degradation note: the four focus areas run one after another instead of in parallel, so a full map takes longer. The output quality is the same — only the wall-clock differs.

Focus areas (run each in turn)

  1. TechnologySTACK.md — languages, frameworks, build tooling, dependencies.
  2. ArchitectureARCHITECTURE.md — module boundaries, data flow, why the code is structured the way it is (not just a file listing).
  3. QualityTESTING.md / CONVENTIONS.md — test posture, coverage gaps, conventions.
  4. ConcernsCONCERNS.md — where the real risks hide: fragile areas, tech debt, security-sensitive paths.

Rules

  • Cite every finding with at least one repo-relative file path (e.g. scripts/state-read.sh). Never assert without evidence. Never use absolute paths.
  • Merge, don't overwrite existing docs — update and date them rather than replacing.
  • Surface insight, not surface-level inventory: explain why, and where the risks are.
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. 5d ago First seen · 35 lines · 88 tokens per session scan A 3e60c591db08

Subscribe to this mod's changes

shipyard-map is a skill published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 468 once invoked, about $0.0004 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 2026-08-30.