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 grutino/mtg-forja --skill skillgit clone --depth 1 https://github.com/grutino/mtg-forjaWrote 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/grutino/mtg-forja/skill)<a href="https://agentmods.dev/skills/grutino/mtg-forja/skill"><img src="https://agentmods.dev/badge/skills/grutino/mtg-forja/skill/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/grutino/mtg-forja/skill"><img src="https://agentmods.dev/badge/skills/grutino/mtg-forja/skill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.02467 |
| Opus 5.5 | $0.00000 | $0.00987 |
| Sonnet 5.5 | $0.00000 | $0.00493 |
| Haiku 4.5 | $0.00000 | $0.00247 |
Grade A, and why
mtg-forja 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 4d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MTG Forja
Cómo analizar un mazo de Magic sin inventarse nada.
El reparto
La forja no analiza. Trae los hechos (oráculo, tipos, costes, rulings oficiales de Wizards vía Scryfall), comprueba el análisis y lo dibuja. El análisis lo haces tú como experto, o el modelo que la persona indique, y lo firmas.
Antes la forja deducía sinergias con patrones de texto. Inventaba jugadas («Ganar vida a escala de tu mano» para un planeswalker que no da vida), tomaba el texto recordatorio por efectos reales y no entendía las mecánicas nuevas (empower, behold). Por eso se quitó: un análisis que suena seguro y está mal es el peor resultado posible.
La regla que lo gobierna todo
Nunca afirmes lo que hace una carta desde la memoria. Lee su oráculo y sus rulings
con datos_para_analisis. Y no te quedes solo en la carta: hay muchísimo escrito
sobre cada mazo, mecánica y metajuego. Consúltalo.
Flujo de trabajo
- Hechos.
datos_para_analisis(lista)(CLI:mtg-forja datos LISTA): por carta, oráculo, tipo, coste, palabras clave y rulings oficiales. Ninguna interpretación. - Investigar. Busca en internet antes de opinar, y guarda cada URL que uses:
- Reglas: el oráculo y los rulings ya los tienes; para mecánicas nuevas, el artículo de mecánicas de la colección en magic.wizards.com.
- Listas reales: MTGGoldfish, MTGDecks, MTGTop8, Untapped.gg (Arena), Moxfield. ¿Quién juega este arquetipo, con qué cartas y con qué resultados?
- Metajuego y análisis: magic.gg (Metagame Mentor), Draftsim, Card Kingdom Blog, CoolStuffInc, 17Lands para limitado.
- Combos:
combos_conocidos(Commander Spellbook) es una fuente más. - Legalidad: comprueba el formato y la próxima rotación si aplica.
- Pensar como experto. Con el oráculo delante:
- ¿cómo gana el mazo, exactamente? ¿Qué cartas son el plan y cuáles lo protegen?
- ¿a quién alcanza cada efecto, y a quién no? (los rulings lo dicen)
- ¿qué se estorba entre sí? ¿qué secuencia de turnos hace que funcione?
- ¿el texto que lees es efecto o es texto recordatorio entre paréntesis?
- ¿cómo de bueno es el mazo frente al metajuego real, y por qué?
- Escribir
analisis.json(formato abajo). - Validar.
validar_analisis(lista, analisis)devuelve los problemas. Corrígelos; no los esquives quitando citas. - Forjar.
forjar(lista, analisis, incrustar_imagenes=...)(CLI:mtg-forja forjar LISTA -a analisis.json [--incrustar-imagenes]). Si el análisis no valida, no se genera nada. Usaincrustar_imagenescuando el HTML se vaya a ver en el visor del chat, que bloquea las imágenes externas.
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.
- 4d ago Changed · +19 lines 172eb285fcab
- 6d ago Changed · -28 lines 253f4fd01758
- 1mo ago First seen · 175 lines · 0 tokens per session scan A f01f9c7a0166
mtg-forja is a skill published in the GitHub repository grutino/mtg-forja (0 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,467 tokens. 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
mtg-rules
Magic: The Gathering comprehensive rules reference and rules engine. Use this skill whenever the user asks about MTG rules, card interactions, game mechanics, timing, priority, layers, state-based actions, combat, stack resolution, or any rules question about Magic: The Gathering. Also trigger on: 'how does X work in…
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
motion
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.