map-me

map-me is a skill for Claude Code, Codex from Kerliula/ship-me. It costs 169 tokens per session (1,549 once invoked), scanned A, original, MIT.

A tool that turns the written outputs of a software-planning pipeline into a plain-language map of its decisions, files, and uncovered gaps.

In plain words
What is it for?
Use it after problem analysis, solution design, implementation, and verification to review what is covered and what still needs attention.
Why use it?
It makes missing links and important holes easier to see than when reading several project documents separately.

Skill for Claude CodeCodex

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/kerliula/ship-me/map-me
Any agent
npx skills add Kerliula/ship-me --skill map-me
Clone the repo
git clone --depth 1 https://github.com/Kerliula/ship-me

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.

agentmods badge for map-me

README.md
[![agentmods](https://agentmods.dev/badge/skills/kerliula/ship-me/map-me.svg)](https://agentmods.dev/skills/kerliula/ship-me/map-me)
Your own site
<a href="https://agentmods.dev/skills/kerliula/ship-me/map-me"><img src="https://agentmods.dev/badge/skills/kerliula/ship-me/map-me.svg" alt="Measured on agentmods" height="20"></a>
Per session 169 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,549 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 5.1 $0.00169 $0.01549
Opus 5 $0.00084 $0.00775
Sonnet 5 $0.00034 $0.00310
Haiku 4.5 $0.00017 $0.00155

Measured 5d ago against content hash 93587343df12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

map-me 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.

The scan reads SKILL.md. This mod also ships 1 executable file (map-me.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/map-me/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Map Me — Show the Holes

The structure of the work is already readable in the four markdown files. The holes are not. That's what this skill is for.

You invent nothing here. Every node and edge is already written down by /grill-me, /solve-me, /build-me and /verify-me. A script parses them; your job is to read the result back in plain language and say which holes actually matter.

A script parses, you narrate. Never hand-derive the graph by reading the artifacts yourself — it's slow, it drifts between runs, and the whole value of the map is that it says the same thing every time.


Step 1 — Run the generator

The script ships next to this file. From the project root:

node ~/.claude/skills/map-me/map-me.mjs

If the skills were installed into a single project, use .claude/skills/map-me/map-me.mjs instead.

Options:

  • --docs <dir> — where the artifacts live (default docs)
  • --out <dir> — where the map goes (default <docs>/map)
  • --slug <slug> — map one run only
  • --brief — print only what changed since the last run
  • --quiet — no stdout summary

Two modes

/map-me invoked by the developer uses the full mode above: it rebuilds everything and you read the holes back in priority order.

The other five skills call the same script with --brief every time they write an artifact, so the map is never stale mid-pipeline. In that mode it prints only the holes that opened or closed since the last run, and prints nothing at all when nothing changed. That's deliberate: a map that re-reports all sixteen holes after every commit is a map people stop reading, which is the problem this whole thing exists to fix.

--brief also exits quietly when there's nothing to map yet, so an early phase can call it safely.

It writes:

File What it is
docs/map/index.html the graph, standalone, opens in any browser
docs/map/HOLES.md every hole, grouped, worst first
docs/map/*.md one note per node — open docs/map/ as an Obsidian vault
docs/map/map.json the raw graph, if something else wants it

Read the full file on GitHub · 155 lines

Files

What ships with it

1 file 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.

  1. 5d ago First seen · 155 lines · 169 tokens per session scan A 93587343df12

Subscribe to this mod's changes

map-me is a skill published in the GitHub repository Kerliula/ship-me (1 stars, last pushed 7d ago), licensed MIT. It adds 169 tokens to every session and 1,549 once invoked, about $0.0008 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

laravel-spatie-event-sourcing

Use this skill any time a user works with Laravel and event sourcing together — whether setting up spatie/laravel-event-sourcing for the first time, designing a new event-sourced domain (aggregates, events, projectors, reactors), generating code for bounded contexts, or debugging issues with AggregateRoot…

albertoarena/claude-laravel-event-sourcing · 150 tokens

filament-plugin-development

Build and publish custom Filament plugins (Filament is the Laravel admin-panel framework). Use when creating a Filament plugin/package, implementing the Plugin contract, scaffolding from the plugin skeleton, registering assets/resources/pages/render-hooks, making a configurable plugin, testing it, or publishing to…

majdghithan/agent-skills · 105 tokens

laravel-architecture-review

Review a Laravel codebase's architecture and design, not just its types. Use when asked to audit a Laravel app, find architectural smells, decide where business logic belongs (controller vs Action vs Service), whether a Repository/DDD/TDD layer is justified, or how to apply SOLID/DRY to a Laravel project. Runs the…

majdghithan/agent-skills · 188 tokens

loop-setup

Session 0. Sets up the loop in this project - detects the stack, checks which connections actually work (git, database, browser, payments sandbox), asks the few decisions only the owner can make, and writes the .loop/ files. Run this once per project, before any planning or building.

cbdreamer11/CB-loop-kit-claude-plugin · 65 tokens

laravel-mixpost

Self-host and operate Mixpost (the open/self-hosted social-media scheduler by Inovector) inside a Laravel app - install, edition choice (Lite vs Pro/Team vs Enterprise), Horizon/Redis/queue setup, connecting providers (LinkedIn, Meta/Facebook/Instagram, TikTok, YouTube), scheduling posts, uploading media, and the…

majdghithan/agent-skills · 129 tokens

laravel-upgrade

Upgrade a Laravel application across major versions safely (Laravel 8 -> 9 -> 10 -> 11 -> 12 -> 13), one hop at a time. Use when upgrading Laravel, when a composer update fails after a major bump, when deciding whether to hop versions by hand or pay for Laravel Shift, or when something compiled fine but broke at…

majdghithan/agent-skills · 174 tokens