What is shipkit-architecture-map?

A code-derived map of a software system's current structure, including applications, data stores, contracts, and integrations. It is kept separately from an architecture decision log, which records why choices were made.

Use it to create or refresh the architecture map and answer questions about runnable services, frontends, workers, command-line tools, libraries, databases, and external connections.

It gives developers a current view of what the codebase contains and highlights when that view may be stale after major structural changes.

shipkit-architecture-map — Skill for Claude Code and Codex by stefan-stepzero: A code-derived map of a software system's current structure…

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/stefan-stepzero/shipkit/shipkit-architecture-map

Any agent

npx skills add stefan-stepzero/shipkit --skill shipkit-architecture-map

Clone the repo

git clone --depth 1 https://github.com/stefan-stepzero/shipkit

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-architecture-map.svg)](https://agentmods.dev/skills/stefan-stepzero/shipkit/shipkit-architecture-map)

Your own site

<a href="https://agentmods.dev/skills/stefan-stepzero/shipkit/shipkit-architecture-map"><img src="https://agentmods.dev/badge/skills/stefan-stepzero/shipkit/shipkit-architecture-map.svg" alt="Measured on agentmods" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,641 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.

Model	Per session	Once invoked
Fable 5	$0.00057	$0.02641
Opus 5	$0.00028	$0.01321
Sonnet 5	$0.00011	$0.00528
Haiku 4.5	$0.00006	$0.00264

Measured 3d ago against content hash d6d98c09d8a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipkit-architecture-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 3d 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.

install/skills/shipkit-architecture-map/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipkit-architecture-map — Living Architecture Map

Purpose: Maintain .shipkit/architecture-map.json — a continuously-refreshable, code-derived answer to "what does the system currently look like?" (applications, datastores, contracts, integrations). It is the what-is map.

This is distinct from .shipkit/architecture.json, which is the why — the append-only decisions log. This skill never reads or writes architecture.json; the two artefacts coexist (decisions vs current-state).

When to Invoke

User triggers:

"Map the architecture"
"What does the system currently look like?"
"Refresh the architecture map"
"Show me applications / datastores / contracts / integrations"

Auto-suggested when:

No .shipkit/architecture-map.json exists and the repo has real source code
The existing map is older than 14 days (staleness)
A major structural change landed (new service, new datastore, new external integration)

What This Map Contains

Section	What it captures	ID prefix
`applications`	Deployable/runnable units: services, frontends, workers, CLIs, libraries	`APP-NNN`
`datastores`	Persistence: postgres, redis, s3, sqlite, mongo, etc.	`DS-NNN`
`contracts`	Interface/data shapes at boundaries: REST/GraphQL routes, events, RPC, shared types	`CON-NNN`
`integrations`	External systems: third-party APIs, webhooks, queues, SaaS	`INT-NNN`

IDs are stable cross-references: datastores[].ownedBy points at an APP-NNN, contracts[].boundary names APP-NNN -> APP-NNN, integrations[].usedBy points at an APP-NNN.

Full schema: references/output-schema.md · Realistic example: references/example.json

Process

Completion Tracking (MANDATORY)

Before starting, create one task per section so coverage is provable:

TaskCreate: "Staleness check + load prior map (preserve IDs)"
TaskCreate: "Read upstream hints (codebase-index, engineering-definition)"
TaskCreate: "Derive applications (APP-*)"
TaskCreate: "Derive datastores (DS-*)"
TaskCreate: "Derive contracts (CON-*)"
TaskCreate: "Derive integrations (INT-*)"
TaskCreate: "Write architecture-map.json (replace)"
TaskCreate: "Verify cross-references resolve + no empty required sections"

Read the full file on GitHub · 221 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago First seen · 221 lines · 57 tokens per session scan A d6d98c09d8a5

Subscribe to this mod's changes

shipkit-architecture-map is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 2,641 once invoked, about $0.0003 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.

ai-tools anthropic claude claude-code claude-skills developer-tools

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

golden-rss

Use when testing the rss golden build.

yusufkaraaslan/Skill_Seekers · 12 tokens

overleaf-sync

Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…

wanshuiyin/Auto-claude-code-research-in-sleep · 97 tokens

shipkit-architecture-map