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 partial-edit-protocolgit 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/partial-edit-protocol)<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/partial-edit-protocol"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/partial-edit-protocol/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/partial-edit-protocol"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/partial-edit-protocol.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 | $0.00066 | $0.00817 |
| Opus 5.5 | $0.00026 | $0.00327 |
| Sonnet 5.5 | $0.00013 | $0.00163 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
partial-edit-protocol 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 2mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Partial Edit Protocol
Objetivo
Evitar que code-writer malinterprete instrucciones de edición parcial, suprimiendo o sobrescribiendo contenido que debería mantenerse intacto.
Regla de oro
Nunca asumas que code-writer infiere qué parte debe conservarse. Siempre debes especificar explícitamente los límites del cambio.
Cuándo usarla
Siempre que delegues a code-writer la modificación de UNA PARTE de un archivo existente (no la creación completa ni el reemplazo total).
Cómo describir el cambio según el tamaño del archivo
Caso A: Archivo pequeño (< 50 líneas o < 2000 caracteres)
Muestra el contenido COMPLETO del archivo actual y el COMPLETO del archivo modificado. Usa "Debe quedar:" seguido del archivo completo.
✅ Correcto:
Archivo: ejemplo.ts
ACTUAL:
import { Component } from '@angular/core';
...
DEBE QUEDAR:
import { Component, signal } from '@angular/core';
...
Caso B: Archivo mediano/grande (≥ 50 líneas)
Muestra SOLO el fragmento relevante, pero con:
- Números de línea de referencia
- 3-5 líneas de contexto ANTES y DESPUÉS del cambio
- Marcadores
← INICIO CAMBIOy← FIN CAMBIO - Frase explícita: "Todo el resto del archivo debe mantenerse intacto."
✅ Correcto:
Archivo: game.service.ts (120 líneas total)
Cambio en líneas 42-45:
// updateScore() ← CONTEXTO (línea 40)
// checkCollision() ← CONTEXTO (línea 41)
jump() { ← INICIO CAMBIO
this._jumping.set(true);
this._velocity.set(-14);
} ← FIN CAMBIO
// render() ← CONTEXTO (línea 47)
// updateObstacles() ← CONTEXTO (línea 48)
Todo el resto del archivo (líneas 1-41 y 46-120) debe mantenerse intacto.
❌ Incorrecto (causó el error del qa-validator):
Prompt actual (solo la parte final): ← AMBIGUO
NUNCA edites archivos directamente.
CRITERIO DE ÉXITO: ...
Debe quedar:
NUNCA edites archivos directamente.
CRITERIO DE ÉXITO: ... (sin afterNextRender)
Caso C: Archivo JSON con prompts de agentes
Siempre mostrar el prompt COMPLETO (suele ser < 100 líneas). Indicar exactamente qué línea o frase cambia. Usar node -e programático.
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.
- 2mo ago First seen · 94 lines · 66 tokens per session scan A 77eca57267a9
partial-edit-protocol is a skill published in the GitHub repository cruzs85/opencode-multiagente-local-37-iterations (5 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 817 once invoked, about $0.0003 per session on Opus 5.5. 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.
partial-edit-protocol compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| partial-edit-protocolcruzs85/opencode-multiagente-local-37-iterations | Skill | 5 | 3mo ago | MIT | A | 66 | OpenCode |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 3d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 6d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |