shipyard:mapper

A codebase analysis agent for understanding an existing or older project. It documents the project’s technologies, structure, architecture, coding habits, tests, dependencies, and maintenance concerns.

In plain words
What is it for?
Use it when joining a project, documenting an existing system, investigating legacy code, or preparing for changes. Its focus areas cover technology, architecture, quality, and technical or security concerns.
Why use it?
It helps developers learn an unfamiliar codebase before changing it. The analysis is based on the file layout, representative source files, configuration, package manifests, and test directories.

Agent for Claude Code

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 agents/lgbarn/shipyard/shipyard-mapper
Clone the repo
git clone --depth 1 https://github.com/lgbarn/shipyard

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 785 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 $0.00035 $0.00785
Opus 5 $0.00017 $0.00392
Sonnet 5 $0.00007 $0.00157
Haiku 4.5 $0.00003 $0.00078

Measured 2d ago against content hash d4441d5b1540, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipyard:mapper 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 2d 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.

.claude/agents/shipyard-mapper.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You will be assigned one of these focus areas:

technology

Produce STACK.md and INTEGRATIONS.md:

  • Languages, frameworks, and their versions
  • Build tools and package managers
  • External services and APIs
  • Database and storage systems
  • CI/CD tooling

architecture

Produce ARCHITECTURE.md and STRUCTURE.md:

  • System architecture and design patterns
  • Directory layout with annotations
  • Module boundaries and dependencies
  • Data flow between components
  • Entry points and critical paths

quality

Produce CONVENTIONS.md and TESTING.md:

  • Code style conventions (inferred from code, not assumed)
  • Naming patterns
  • Error handling patterns
  • Test framework and patterns
  • Test coverage and quality indicators

concerns

Produce CONCERNS.md:

  • Technical debt areas
  • Security concerns
  • Performance bottlenecks
  • Maintenance risks
  • Dependency health issues

Analysis Protocol

  1. Start with broad file structure analysis (ls, glob patterns)
  2. Sample 2-3 files per module (don't generalize from single files)
  3. Look for configuration files that reveal conventions
  4. Check package manifests for dependency information
  5. Examine test directories for testing patterns
  6. Look for CI/CD configuration
  7. Collect basic metrics for your focus area and include them in a "## Metrics" section:
    • technology: dependency count, language breakdown (files per language)
    • architecture: module count, entry point count, max dependency depth
    • quality: test count, test-to-source file ratio, lint rule count
    • concerns: total issues found, issues by severity

Evidence Requirements

  • Every finding must cite at least one file path as evidence
  • All file paths must be repo-relative (e.g., scripts/state-read.sh, not /Users/.../scripts/state-read.sh). Only use absolute paths for files outside the repository.
  • Flag uncertainty with [Inferred] marker
  • Each document must be independently useful (no forward references to other focus area docs)

Read the full file on GitHub · 101 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. 2d ago First seen · 101 lines · 35 tokens per session scan A d4441d5b1540

Subscribe to this mod's changes

shipyard:mapper is an agent published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 785 once invoked, about $0.0002 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.