mars-development

mars-development is a skill for Claude Code from andrea-magni/MARS. It costs 155 tokens per session (1,471 once invoked), scanned A, original, MPL-2.0.

A development guide for building REST APIs with MARS-Curiosity, a Delphi library that maps web requests to ordinary Delphi classes. It covers routes, authentication, data responses, events, templates, clients, configuration, and serialization.

In plain words
What is it for?
Use it to create REST resources and endpoints, bind request parameters, protect routes with JWT tokens and roles, publish FireDAC data, send server-sent events, and render HTML with WebStencils.
Why use it?
It explains how MARS connects HTTP requests to Delphi code and handles common API concerns. This reduces the work of designing each server feature from first principles.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the MARS plugin — 3 skills shipped together

Good fit Use it to create REST resources and endpoints, bind request parameters, protect routes with JWT tokens and roles, publish FireDAC data, send server-sent events, and render HTML with WebStencils.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andrea-magni/mars/mars-development
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.

Any agent
npx skills add andrea-magni/MARS --skill mars-development
Clone the repo
git clone --depth 1 https://github.com/andrea-magni/MARS

Made for: Claude Code.

Or install MARS, the plugin that ships this one along with the rest of its 3 skills.

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 mars-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/andrea-magni/mars/mars-development/github.svg)](https://agentmods.dev/skills/andrea-magni/mars/mars-development)
Your own site
<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.

agentmods 80×15 button for mars-development

Your own site · 80×15
<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>
Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,471 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00155 $0.01471
Opus 5 $0.00077 $0.00736
Sonnet 5 $0.00031 $0.00294
Haiku 4.5 $0.00015 $0.00147

Measured 9d ago against content hash e242dd399ca4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

Skills/mars-development/SKILL.md · 81 lines

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, usually TServerEngine.Default in Server.Ignition.pas): owns HTTP-level config (port, base path /rest, CORS, compression) and one or more Applications added with AddApplication('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 via MARSRegister(TMyResource) (or MARSRegister([TResA, TResB]), or TMARSResourceRegistry.Instance.RegisterResource<TMyResource>) in the unit initialization. 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.

Read the full file on GitHub · 81 lines

Files

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.

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. 9d ago First seen · 81 lines · 155 tokens per session scan A e242dd399ca4

Subscribe to this mod's changes

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.