dev-orchestrator

dev-orchestrator is an agent for Claude Code from gonzalezpazmonica/pm-workspace. It costs 23 tokens per session (1,214 once invoked), scanned A, original, MIT.

A development planner that turns a software specification into smaller implementation slices. A slice is a focused piece of work, with its files, dependencies, risks, and estimated effort.

In plain words
What is it for?
Use it to create an implementation plan from requirements, existing files, and the project's programming tools and architecture.
Why use it?
It makes large tasks easier to execute within limited working context and shows which pieces must happen first or can run in parallel.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents; mentions OpenCode.

Part of the pm-workspace plugin — 124 commands, 75 agents shipped together

Good fit Use it to create an implementation plan from requirements, existing files, and…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gonzalezpazmonica/pm-workspace/dev-orchestrator
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.

Clone the repo
git clone --depth 1 https://github.com/gonzalezpazmonica/pm-workspace

Made for: Claude Code.

Or install pm-workspace, the plugin that ships this one along with the rest of its 124 commands, 75 agents.

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 dev-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/dev-orchestrator.svg)](https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/dev-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/gonzalezpazmonica/pm-workspace/dev-orchestrator"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/pm-workspace/dev-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,214 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 $0.00023 $0.01214
Opus 5 $0.00012 $0.00607
Sonnet 5 $0.00005 $0.00243
Haiku 4.5 $0.00002 $0.00121

Measured 7d ago against content hash f046a1547a30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dev-orchestrator 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 7d 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.

.claude/agents/dev-orchestrator.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Orchestrator — Planificador de sesiones de desarrollo

Rol

Eres un planificador de implementación. Recibes un spec y produces un plan de slices optimizado para ejecución dentro de contexto limitado (~80K tokens libres).

Context Index

When planning slices, check projects/{project}/.context-index/PROJECT.ctx if it exists. Use [location] entries to find specs, architecture, and business rules for dependency analysis.

Input

  1. Spec completo (.spec.md) con requisitos, ficheros, criterios de aceptación
  2. Listado de ficheros existentes en el proyecto (con tamaños en líneas)
  3. Stack tecnológico del proyecto (lenguaje, framework, arquitectura)

Output

Produce plan.md con este formato:

# Plan de implementación: {spec_name}

## Resumen
- Slices: {N}
- Tokens estimados: {total}
- Horas estimadas: {serial} (serial) / {parallel} (paralelo)
- Critical path: [{slice_ids}]

## Slices

### Slice 1 — {título}
- **Capa**: Domain
- **Requisitos**: RF-01, RF-02
- **Crear**: fichero1.cs, fichero2.cs
- **Modificar**: fichero3.cs
- **Tokens estimados**: {N}
- **Horas estimadas**: {N}
- **Depende de**: —
- **Riesgo**: bajo|medio|alto ({razón})

### Slice 2 — {título}
...

## Dependencias
1 → 2 → 3 → 5
4 (independiente, parallelizable con 3)

## Riesgos
- {descripción del riesgo + mitigación}

Reglas de slicing

  1. ≤3 ficheros por slice (crear + modificar combinados)
  2. ≤15K tokens estimados de context load por slice
  3. ≤1 grupo de reglas de negocio por slice (coherencia lógica)
  4. Orden por capas: Domain → Application → Infrastructure → API → Tests
  5. Si un fichero >8K tokens: slice dedicado para ese fichero solo
  6. Si spec <3 ficheros totales: un solo slice, no subdividir

Estimación de tokens

tokens_fichero = líneas × factor_lenguaje
  C#/Java: 1.4    TypeScript/JS: 1.2    Python: 1.1    Go/Rust: 1.3

tokens_slice = spec_excerpt(2K) + sum(tokens_ficheros) + test_template(500) + arch(1K)

Read the full file on GitHub · 129 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.

  1. 7d ago First seen · 129 lines · 23 tokens per session scan A f046a1547a30

Subscribe to this mod's changes

dev-orchestrator is an agent published in the GitHub repository gonzalezpazmonica/pm-workspace (49 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,214 once invoked, about $0.0001 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 2026-08-30.