What is task-decomposition?

A task-planning guide for the RouteTracker app, which uses Angular 21 and signals for managing changing data. It turns broad requests into ordered instructions for a coding agent.

Use it to break a RouteTracker feature or fix into small, file-specific steps. It also defines the project's Angular rules and success checks for the agent doing the implementation.

It removes uncertainty about what to change, where to change it, and how to check the result. It also separates package setup, interface changes, service logic, API work, and testing.

task-decomposition — Skill for OpenCode by cruzs85

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 task-decomposition

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/task-decomposition/github.svg)](https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/task-decomposition)

Your own site

<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/task-decomposition"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/task-decomposition/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/task-decomposition"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/task-decomposition.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,153 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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.01153
Opus 5.5	$0.00020	$0.00461
Sonnet 5.5	$0.00010	$0.00231
Haiku 4.5	$0.00005	$0.00115

Measured 2mo ago against content hash f941e74c3fb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

task-decomposition 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.

configuraciones/configuracion-1(route-tracker-v1)/.opencode/skills/task-decomposition/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Objetivo

Transformar una solicitud general en una lista de pasos claros, secuenciales y verificables que puedan ser ejecutados por un agente de código sin necesidad de razonamiento complejo.

CLASIFICACIÓN DE TAREA (OBLIGATORIO)

Antes de descomponer, clasificar la tarea en:

package-installation
ui-refactor
service-logic
api-integration
testing

Luego:

Si es package-installation → delegar a @package-manager
Si es ui-refactor → delegar a @code-writer
Si es mixta → dividir por tipo de agente

REGLAS GENERALES

SIEMPRE dividir en pasos numerados y secuenciales
Cada paso debe afectar SOLO un archivo o responsabilidad clara
SIEMPRE indicar rutas exactas de archivos (src/app/...)
NUNCA usar lenguaje ambiguo:
- ❌ "ajustar", "mejorar", "revisar"
- ✅ "crear", "modificar", "añadir", "reemplazar"
NUNCA escribir código — solo instrucciones
Incluir SIEMPRE criterios de éxito verificables

REGLAS ESPECÍFICAS DEL PROYECTO

Arquitectura Angular

Componentes: standalone (NO NgModules)
Servicios: providedIn: 'root'
Estado SIEMPRE con signals
Templates con @if, @for (NO *ngIf/*ngFor)

Servicios (MUY IMPORTANTE)

Cuando una tarea involucre estado:

Crear signal privado: private readonly _estado = signal<T>(valorInicial)
Exponer como readonly: readonly estado = this._estado.asReadonly()
NO exponer signals mutables

Effects

Si hay interacción con UI o mapa:

Usar effect()
SIEMPRE con { injector }

Leaflet (mapa)

Inicializar en afterNextRender()
Coordenadas:
- Leaflet: [lat, lng]
- APIs externas: revisar conversión

OSRM (si aplica)

Convertir puntos a formato: lng,lat
Convertir respuesta a [lat, lng]
Manejar fallback a línea recta

IndexedDB

Nunca asumir disponibilidad en tests
Si la tarea toca tests: → considerar mocks o polyfills

TIPOS DE TAREAS Y CÓMO DESCOMPONER

1. NUEVA FEATURE

Estructura obligatoria:

Read the full file on GitHub · 206 lines

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.

2mo ago First seen · 206 lines · 50 tokens per session scan A f941e74c3fb3

Subscribe to this mod's changes

task-decomposition is a skill published in the GitHub repository cruzs85/opencode-multiagente-local-37-iterations (5 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 1,153 once invoked, about $0.0002 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.

Planning

task-decomposition next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
task-decompositioncruzs85/opencode-multiagente-local-37-iterations	Skill	5	3mo ago	MIT	A	50	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