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.
npx skills add Kerliula/ship-me --skill solve-megit clone --depth 1 https://github.com/Kerliula/ship-meWrote 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.
[](https://agentmods.dev/skills/kerliula/ship-me/solve-me)<a href="https://agentmods.dev/skills/kerliula/ship-me/solve-me"><img src="https://agentmods.dev/badge/skills/kerliula/ship-me/solve-me.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00113 | $0.02569 |
| Opus 5 | $0.00056 | $0.01285 |
| Sonnet 5 | $0.00023 | $0.00514 |
| Haiku 4.5 | $0.00011 | $0.00257 |
Grade A, and why
solve-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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solve Me — Divide, Compare, Recommend
Your job is to design a solution on paper. No code. No framework names. Plain language only.
You are not allowed to say "use Laravel," "add a migration," "create an Eloquent model," "use Redis," or name any specific library, framework, or tool. Describe things at the level of: what data is stored, what steps happen, what checks are made, in what order, and why. Anyone reading it should be able to build it in any language or stack.
Write in plain, everyday language. Short sentences. Concrete words. If a smart non-technical person couldn't follow a paragraph, rewrite it simpler.
Input
You need a clear problem write-up before you can start. Accept it as:
- A path to a markdown file (e.g. the file
/grill-meproduced atdocs/grilling/<topic>.md), or - Problem details pasted directly into the conversation.
If neither is available, ask the developer for one. Don't invent the problem yourself — a fuzzy or assumed problem produces a fuzzy solution.
Read the problem write-up fully before doing anything else. Pull out: the rules, the limits, the edge cases, what must always stay true, and what's out of scope. These constrain every solution you propose — mention constraints, don't restate the whole doc.
Step 1 — Split the problem (divide)
Break the problem into smaller sub-problems that can mostly be solved on their own. Good ways to split:
- By stage — the steps something goes through, in order (e.g. "receiving the request" → "checking if it's allowed" → "recording the result" → "telling people about it").
- By concern — different jobs that don't depend on each other's internal details (e.g. "deciding who's allowed" vs. "handling two people trying at once" vs. "showing the result to the user").
- By actor — different pieces of behavior for different people or systems involved.
Rules for splitting:
- Each sub-problem should be small enough to explain in a few sentences.
- Each sub-problem should be understandable on its own, without re-explaining the whole problem.
- Don't split something that's genuinely one decision into two sub-problems just to hit a number — a forced split produces fake options later.
- Name each sub-problem with a short, plain title (a question it answers), not a technical label.
- Number them (Sub-problem 1, Sub-problem 2, …) in the order listed
—
/build-me's commit plan refers to these numbers, so never renumber them afterwards.
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.
- 7d ago First seen · 283 lines · 113 tokens per session scan A 2131daaa063d
solve-me is a skill published in the GitHub repository Kerliula/ship-me (1 stars, last pushed 9d ago), licensed MIT. It adds 113 tokens to every session and 2,569 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.
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…
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…
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…
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.
laravel-filament
Version-aware best practices for Filament (the Laravel admin-panel / TALL-stack framework by filamentphp), covering v1 through v5. Use whenever building, reviewing, or upgrading Filament resources, panels, forms/schemas, tables, actions, relation managers, widgets, or multi-tenancy. ALWAYS detects the installed…
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…