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 cruzs85/opencode-multiagente-local-37-iterations --skill contract-consistencygit clone --depth 1 https://github.com/cruzs85/opencode-multiagente-local-37-iterationsWrote 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/cruzs85/opencode-multiagente-local-37-iterations/contract-consistency)<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/contract-consistency"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/contract-consistency/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/cruzs85/opencode-multiagente-local-37-iterations/contract-consistency"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/contract-consistency.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 | $0.00572 |
| Opus 5 | $0.00000 | $0.00286 |
| Sonnet 5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
contract-consistency 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 12d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: contract-consistency
Propósito
Antes de implementar un archivo que dependa de otro, verificar que los contratos (tipos, métodos, propiedades) sean consistentes entre ambos.
¿Cuándo usarla?
Siempre que code-writer vaya a implementar:
- Un componente que llama a un servicio
- Un servicio que implementa una interfaz
- Un servicio que usa tipos definidos en un modelo
- Cualquier archivo que importe de otro archivo del proyecto
Reglas obligatorias
Regla 1: Leer antes de escribir
Antes de escribir un archivo A que depende de un archivo B:
- LEER el archivo B completo
- Identificar TODOS los nombres de métodos, propiedades, tipos e interfaces que A va a usar
- Usar EXACTAMENTE esos nombres — sin cambios, sin "alias", sin "variantes"
Regla 2: Consistencia de tipos literales
Si el modelo define: type: 'cactus' | 'pterodactyl'
El servicio DEBE usar EXACTAMENTE: 'cactus' o 'pterodactyl'
NO usar: 'bird', 'cactus2', 'CACTUS'
Regla 3: Firmas de métodos
Si el servicio define: jump(): void
El componente DEBE llamar: service.jump()
NO llamar: service.doJump(), service.jumpDino(), service.saltar()
Regla 4: Parámetros
Si el servicio define: updateGameLoop(deltaTime: number)
La llamada DEBE incluir: service.updateGameLoop(deltaTime)
NO: service.updateGameLoop() (sin el parámetro requerido)
Regla 5: Retorno de métodos
Si un servicio devuelve un tipo, el componente debe tratar el retorno según ese tipo:
- Si devuelve
ReadonlySignal<GameData>, leer conservice.gameData() - Si devuelve
DinoState, acceder a sus propiedades directamente
Cómo usar esta skill
- Cargar esta skill ANTES de escribir cualquier archivo
- Identificar el archivo del que se depende
- Leer ese archivo con la herramienta
readocat - Escribir el nuevo archivo usando EXACTAMENTE los mismos nombres y tipos
Anti-patrones
❌ Escribir un componente que llama a gameService.jump() sin verificar que jump() existe en GameService
❌ Definir un tipo 'pterodactyl' en el modelo y usar 'bird' en el servicio
❌ Llamar a un método sin pasar los parámetros requeridos
❌ Asumir que un método existe sin leer primero el archivo que lo define
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.
- 12d ago First seen · 54 lines · 0 tokens per session scan A 7f2260a77fc1
contract-consistency is a skill published in the GitHub repository cruzs85/opencode-multiagente-local-37-iterations (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 572 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…