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 andrea-magni/MARS --skill mars-developmentgit clone --depth 1 https://github.com/andrea-magni/MARSWrote 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/andrea-magni/mars/mars-development)<a href="https://agentmods.dev/skills/andrea-magni/mars/mars-development"><img src="https://agentmods.dev/badge/skills/andrea-magni/mars/mars-development/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/andrea-magni/mars/mars-development"><img src="https://agentmods.dev/badge/skills/andrea-magni/mars/mars-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00155 | $0.01471 |
| Opus 5 | $0.00077 | $0.00736 |
| Sonnet 5 | $0.00031 | $0.00294 |
| Haiku 4.5 | $0.00015 | $0.00147 |
Grade A, and why
mars-development 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 9d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developing with MARS-Curiosity
MARS (https://github.com/andrea-magni/MARS) maps HTTP requests onto plain Delphi classes via attributes and RTTI. Runtime model:
- Engine (
IMARSEngine, usuallyTServerEngine.DefaultinServer.Ignition.pas): owns HTTP-level config (port, base path/rest, CORS, compression) and one or more Applications added withAddApplication('DefaultApp', '/default', ['Server.Resources.*'])— the third argument is a list of unit-name masks selecting which registered resources belong to the app. - Resources: classes annotated with
[Path('...')], registered viaMARSRegister(TMyResource)(orMARSRegister([TResA, TResB]), orTMARSResourceRegistry.Instance.RegisterResource<TMyResource>) in the unitinitialization. A new instance is created per request and freed afterwards. - Activation (
IMARSActivation): per-request context (request, response, token, URL...). Injectable anywhere with[Context]. - URL = engine BasePath + app path + resource
[Path]+ method[Path]:/rest/default/customers/123.
Minimal resource
unit Server.Resources.Customers;
interface
uses
SysUtils, Classes
, MARS.Core.Attributes, MARS.Core.MediaType, MARS.Core.JSON;
type
TCustomer = record
Id: Integer;
Name: string;
end;
[Path('customers'), Produces(TMediaType.APPLICATION_JSON)]
TCustomersResource = class
public
[GET]
function List([QueryParam] search: string): TArray<TCustomer>;
[GET, Path('{id}')]
function GetById([PathParam] id: Integer): TCustomer;
[POST, Consumes(TMediaType.APPLICATION_JSON)]
function Add([BodyParam] ACustomer: TCustomer): TCustomer;
end;
implementation
uses
MARS.Core.Registry;
// ... method bodies ...
initialization
MARSRegister(TCustomersResource);
end.
Records, arrays of records, objects, TJSONObject/TJSONArray, strings, numbers, streams and datasets are serialized automatically by the MessageBodyWriter registry; same in reverse for [BodyParam] via MessageBodyReaders. No manual JSON code needed for plain data.
What ships with it
7 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.
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.
- 9d ago First seen · 81 lines · 155 tokens per session scan A e242dd399ca4
mars-development is a skill published in the GitHub repository andrea-magni/MARS (395 stars, last pushed 19d ago), licensed MPL-2.0. It adds 155 tokens to every session and 1,471 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 2026-08-30.
Other skills, from other repositories
horse-database-pooling
Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.
horse-mvc-architecture
Guide for structuring corporate Horse applications using Clean MVC (Model-View-Controller) principles and decoupling HTTP layers from business logic.
horse-request-response
Guide to interacting with THorseRequest (body, query, params, headers) and THorseResponse (Send, Status, ContentType).
horse-dependency-injection
Guide for managing request-scoped contextual services and IoC (dependency injection) in Delphi and Lazarus.
horse-lazarus-compatibility
Guide for ensuring Lazarus and Free Pascal (FPC) compatibility, addressing anonymous methods differences, JSON units, and compiler directives.
horse-middlewares
Guide to using standard Horse middlewares (CORS, Jhonson, compression, basic-auth, logger) and pipeline registration order.