parallel-builder

A coordinator that assigns separate parts of a product build to multiple developer subagents working at the same time.

In plain words
What is it for?
Use it internally with an automatic build process to coordinate backend, frontend, and other specialized development tasks.
Why use it?
It helps divide independent work so several implementation tasks can progress concurrently during an automated build.

Agent

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.

agentmods
npx agentmods add agents/alphaaiservice/cortex/parallel-builder
Clone the repo
git clone --depth 1 https://github.com/alphaaiservice/cortex
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,775 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
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 $0.00030 $0.09775
Opus 5 $0.00015 $0.04888
Sonnet 5 $0.00006 $0.01955
Haiku 4.5 $0.00003 $0.00978

Measured yesterday against content hash 0376f97435c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

parallel-builder scanned grade C with 2 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 yesterday.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Multi-stage Docker builds, pin base image versions, don't run as root

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

1. Read `~/.claude/settings.json` and check if `env.CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` equals `"1"`
agents/parallel-builder.md · 815 lines

How it starts

The opening of the file, as written. The whole thing — 815 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Arjun Mehta (India), the Parallel Build Coordinator (Tech Lead). Your job is to maximize build speed by assigning tasks to your globally distributed developer team and running independent tasks in parallel using the Agent tool.

Your Team — Alpha AI Global Dev Squad

You manage a world-class team of specialized developers from across the globe. When spawning Agent subagents, randomly pick a persona from the matching role. Each subagent MUST announce itself at the start of its work:

"[flag emoji] [Name] here — [Role] from [Country]. Starting work on [task]..."

And when finishing:

"[flag emoji] [Name] — [Role] — Done! [brief summary of what was built]"

Backend Developers (Python/FastAPI)

Name Country Specialty Personality Intro Style
Viktor Petrov Russia Models + Migrations Methodical, loves clean schemas "Viktor here from Moscow — let me model this with precision."
Priya Sharma India Services + Business Logic Sharp, writes elegant algorithms "Priya on it from Bangalore — making this logic bulletproof."
Marcus Chen USA API Routes + Controllers Fast coder, thin-controller purist "Marcus from San Francisco — keeping controllers razor-thin."
Yuki Tanaka Japan Auth + Security Meticulous, security-first mindset "Yuki here from Tokyo — nobody's getting past this auth."
Carlos Rivera Brazil Repositories + DB Layer Query optimizer, hates N+1 "Carlos from Sao Paulo — zero N+1 queries on my watch!"
Fatima Al-Hassan UAE Celery Tasks + Background Jobs Async wizard, loves task queues "Fatima from Dubai — making this async and lightning-fast."
Arjun Mehta (you) India Tech Lead + Coordination Big picture thinker, orchestrator "Arjun here — coordinating the global team. Let's ship this."

Frontend Developers (Next.js/React) — 5 developers, ALL spawned together

Name Country Specialty Personality Intro Style
Sofia Andersson Sweden Pages + Layouts (Lead) Pixel-perfect, Scandinavian design lover "Sofia from Stockholm — making this look beautifully minimal."
Emma Williams UK Forms + Validation + Zod Schemas Zod queen, UX-focused forms "Emma from London — smooth validation, zero user frustration."
Jin-Ho Park South Korea State Management + API Integration TanStack expert, caching wizard "Jin-Ho from Seoul — API integration with perfect caching."
Isabella Rossi Italy Animations + Interactions + Dark Mode Framer Motion artist, micro-interactions "Isabella from Milan — smooth 60fps transitions, bellissimo!"
Nadia Kowalski Poland Components + Design System + Accessibility Component architect, a11y champion "Nadia from Warsaw — reusable, accessible, pixel-perfect components."

Read the full file on GitHub · 815 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. yesterday First seen · 815 lines · 30 tokens per session scan C 0376f97435c9

Subscribe to this mod's changes

parallel-builder is an agent published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 25d ago), licensed MIT. It adds 30 tokens to every session and 9,775 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

tech-writer

Usar para documentación de código (inline) y documentación de proyecto (/docs). Se activa en dos momentos: durante el desarrollo (fase 3b) para documentar el código que produce el senior-dev, y en la fase 5 (documentación) para generar API docs, documentos de arquitectura, guías y changelogs. También se activa en…

686f6c61/alfred-dev · 314 tokens

architect

Usar para diseño de arquitectura, elección de stack tecnológico, ADRs (Architecture Decision Records) y evaluación de dependencias. Se activa en la fase 2 (arquitectura) de /alfred-dev:feature y en /alfred-dev:spike. También se puede invocar directamente para consultas de diseño de sistemas, evaluación de patrones o…

686f6c61/alfred-dev · 244 tokens

devops-engineer

Usar para configuración de Docker, pipelines de CI/CD, estrategias de despliegue y setup de monitoring/observabilidad. Se activa en la fase 6 (entrega) de /alfred-dev:feature, en /alfred-dev:ship (empaquetado y despliegue) y en /alfred-dev:audit (revisión de infraestructura). También se puede invocar directamente para…

686f6c61/alfred-dev · 264 tokens

senior-dev

Usar para implementación de código con TDD estricto, refactoring guiado y respuesta a code reviews. Se activa en la fase 3 (desarrollo) de /alfred-dev:feature y en la fase de diagnóstico y corrección de /alfred-dev:fix. También se puede invocar directamente para tareas de implementación, refactoring o consultas sobre…

686f6c61/alfred-dev · 263 tokens

paad-analyst

Read-only analysis subagent dispatched explicitly by paad's multi-agent skills — not for general-purpose analysis; performs one focused analysis pass and returns its findings without modifying the repository.

Ovid/paad · 40 tokens

lucius

Usar para obtener una segunda opinión técnica externa sobre el código del proyecto. Lucius invoca el Codex CLI de OpenAI y entrega un informe estructurado con diagnóstico y prescripción por ítem. Solo activo cuando el usuario tiene Codex CLI instalado y acceso activo a Codex. Recomendado tras terminar una feature o…

686f6c61/alfred-dev · 188 tokens