post-write-verification

post-write-verification is a skill for OpenCode from cruzs85/opencode-multiagente-local-37-iterations. It costs 51 tokens per session (593 once invoked), scanned A, original, MIT.

A post-writing code review checklist for checking files after they have been changed.

In plain words
What is it for?
Use it after a coding agent writes a batch of files and before the changes move to quality assurance.
Why use it?
It catches unused imports, unused variables, uncalled public methods, arithmetic mismatches, and broken links between files before testing.

Skill for OpenCode

Written for OpenCode: installed under .opencode/.

Good fit Use it after a coding agent writes a batch of files and before the changes move to quality assurance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cruzs85/opencode-multiagente-local-37-iterations/post-write-verification
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 cruzs85/opencode-multiagente-local-37-iterations --skill post-write-verification
Clone the repo
git clone --depth 1 https://github.com/cruzs85/opencode-multiagente-local-37-iterations

Made for: OpenCode.

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 post-write-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/post-write-verification/github.svg)](https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/post-write-verification)
Your own site
<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/post-write-verification"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/post-write-verification/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 post-write-verification

Your own site · 80×15
<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/post-write-verification"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/post-write-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 593 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.
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 $0.00051 $0.00593
Opus 5 $0.00026 $0.00296
Sonnet 5 $0.00010 $0.00119
Haiku 4.5 $0.00005 $0.00059

Measured 9d ago against content hash 84e0d8aa74c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

post-write-verification 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.

configuraciones/configuracion-14(multi-agente)/.opencode/skills/post-write-verification/SKILL.md · 54 lines

What it actually says

Post-Write Verification Checklist — para @verifier

Objetivo

Verificar que el archivo recién escrito está limpio antes de pasarlo a QA. @verifier ejecuta este checklist después de que code-writer complete el lote de escritura.

Regla obligatoria

No dar un lote por verificado hasta que los 5 puntos del checklist estén verificados.


Checklist de verificación (OBLIGATORIO)

@verifier debe leer cada archivo modificado y verificar:

1. 📦 IMPORTS

  • ¿Cada import se usa al menos una vez en el cuerpo del archivo?
  • Si hay imports sin usar → reportar a @code-writer para que los elimine.

2. 🧹 VARIABLES MUERTAS

  • ¿Toda variable, constante o propiedad declarada se referencia en el código?
  • Si hay elementos declarados pero nunca usados → reportar a @code-writer.

3. 📞 MÉTODOS PÚBLICOS

  • ¿Cada método público tiene al menos un callsite potencial?
  • Los métodos privados pueden no tener callsite externo (se llaman internamente).

4. 🔢 COHERENCIA ARITMÉTICA

  • ¿Las operaciones matemáticas combinan variables del mismo dominio?
    • timestamp - lastObstacleTime → ambos deben ser marcas de tiempo (ms)
    • coordenadaX - velocidad → ambos deben ser valores espaciales
    • Si una variable es un timestamp y la otra es una posición X → ❌ BUG
  • NO mezclar timestamps con coordenadas, ni píxeles con segundos, ni metros con kilómetros.
  • ¿El resultado de la operación tiene sentido en el dominio?
    • Si restas dos timestamps, obtienes un delta en ms ✅
    • Si restas un timestamp a una coordenada X, obtienes basura ❌
  • Si usas requestAnimationFrame, considera si necesitas deltaTime.

5. 🔗 CONTRATOS

  • Si el archivo consume o importa otro archivo, verifica que los nombres de métodos, tipos y propiedades coinciden EXACTAMENTE con el archivo fuente.
  • Usa grep para confirmar: grep "nombreMetodo" ruta-del-archivo-fuente.ts

Acción correctiva

Si cualquiera de los puntos falla:

  1. @verifier reporta el hallazgo al orquestador con archivo exacto, línea, esperado vs actual
  2. El orquestador delega la corrección a @code-writer
  3. Una vez corregido, @verifier RE-VERIFICA el archivo
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 · 54 lines · 51 tokens per session scan A 84e0d8aa74c3

Subscribe to this mod's changes

post-write-verification is a skill published in the GitHub repository cruzs85/opencode-multiagente-local-37-iterations (5 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 593 once invoked, about $0.0003 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.