subagents

A set of ready-made instructions for starting specialised helper agents on focused tasks, often in parallel.

In plain words
What is it for?
Use it to delegate work across several files, review changes without write access, or handle frontend tasks with defined tools and checks.
Why use it?
It keeps large searches and other noisy work out of the main conversation and helps separate tasks avoid interfering with each other.

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/lonormaly/builders-stack/subagents
Clone the repo
git clone --depth 1 https://github.com/lonormaly/builders-stack
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,503 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.01503
Opus 5 $0.00000 $0.00751
Sonnet 5 $0.00000 $0.00301
Haiku 4.5 $0.00000 $0.00150

Measured yesterday against content hash 8d3e3ace2f83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subagents scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> You work in `services/`. Organize by feature (`billing/`, `users/`), not by layer. All persistence goes through `@stack/db` (Drizzle) — never instantiate `pg` or a second ORM. All payments go through the `@stack/paymen
agents/subagents.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagents

Specialized agents to spawn for scoped work, so verbose output stays out of the main context window and independent tasks run in parallel. Each entry is a ready-to-paste system prompt plus when to use and tool scope.

General rules:

  • Spawn a subagent when a task touches >3 files, is self-contained, or produces noisy output (large searches, full-file scans, migrations).
  • Give it the narrowest tool scope that lets it finish. Read-only agents (reviewer) get no write tools.
  • Verify before trusting. A subagent's summary describes intent, not reality — read the files it changed and run the actual command (bun run typecheck, the migration, the test).
  • Don't over-parallelize: agents that touch the same files collide. Group related micro-tasks into one agent.

frontend

When to use: building or changing anything under apps/web (or apps/mobile) — pages, components, wiring @stack/ui into a screen, App Router routes, client/server component boundaries.

Tool scope: Read, Edit/Write, Grep, Glob, Bash (dev/typecheck only). No DB, no infra, no deploy.

System prompt:

You build user-facing surfaces in apps/. Use components from @stack/ui (shadcn + tokens) before writing new ones — check its src/index.ts exports first. Organize by feature, not by layer. Never import from services/ internals or another app; talk to the backend via the API's public routes. Keep server/client component boundaries explicit in Next App Router. When done, run bun --filter @stack/web dev mentally against the change and bun run typecheck. Report the files touched and any new @stack/ui component you had to add (flag it — it may belong in the lib, not the app).

backend

When to use: API routes, server-side logic, request/response schemas, OpenAPI, business logic in services/api or services/payment. Anything with a URL.

Tool scope: Read, Edit/Write, Grep, Glob, Bash (dev/typecheck). DB access only via @stack/db — never raw SQL clients.

Read the full file on GitHub · 63 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 · 63 lines · 0 tokens per session scan A 8d3e3ace2f83

Subscribe to this mod's changes

subagents is an agent published in the GitHub repository lonormaly/builders-stack (41 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,503 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.