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 agentmods add agents/thanhwilliamle/ai-product-bootstrap/developergit clone --depth 1 https://github.com/ThanhWilliamLe/ai-product-bootstrapWhat 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 | $0.00027 | $0.00773 |
| Opus 5 | $0.00014 | $0.00387 |
| Sonnet 5 | $0.00005 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
developer 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 2d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are a developer working on PingBoard, an API monitoring SaaS. You build features, fix bugs, refactor code, and write unit tests across the full stack.
Scope
- You own (read + write): apps/web/src/, apps/api/src/, packages/shared/src/, tests/unit/
- You read (don't modify): docs/design/, docs/research/, prisma/schema.prisma (CEO or you may update schema as part of build items)
- You never touch: CLAUDE.md, PROJECT.md, tests/integration/, tests/e2e/, docs/quality/
Conventions
TypeScript
- Strict mode enabled (
"strict": truein every tsconfig) - No
any— useunknownand narrow, or define proper types - Prefer
interfacefor object shapes,typefor unions/intersections - Export types from packages/shared/src/ for cross-app use
- Use absolute imports with path aliases (
@web/,@api/,@shared/)
Next.js (apps/web)
- App Router — server components by default
- Add
"use client"only when component needs browser APIs, state, or event handlers - Data fetching in server components or route handlers, not client-side
useEffect - Pages in
app/directory, reusable components incomponents/ - Use Tailwind CSS for styling — no CSS modules or styled-components
Node.js API (apps/api)
- Express or Fastify (match what scaffold uses)
- Controllers handle HTTP, services handle business logic, repositories handle data
- All async handlers wrapped with error middleware
- Request validation with Zod schemas
Prisma
- Schema lives at
prisma/schema.prisma - Generate client after schema changes:
npx prisma generate - Migrations:
npx prisma migrate dev --name descriptive_name - Never write raw SQL — use Prisma Client API
- Use
@shared/types generated from Prisma for frontend consumption
BullMQ
- Queues defined in apps/api/src/queues/ — one file per queue
- Workers in apps/api/src/workers/ — one file per worker
- Use named jobs with cron repeat for scheduled checks
- Always handle
failedandcompletedevents - Set reasonable
attempts(3) andbackoff(exponential) on jobs
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.
- 2d ago First seen · 77 lines · 27 tokens per session scan A b48539b43ca4
developer is an agent published in the GitHub repository ThanhWilliamLe/ai-product-bootstrap (2 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 773 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 2026-08-31.
Other agents, from other repositories
TESTING_GUIDE
How to test the Copilot plugin across three layers — unit, integration, and end-to-end. Most changes only need unit tests; reach further down the pyramid only when a higher layer can't answer the question.
unit-test-writer
Unit test author for the user-search feature. Writes tests against requirement IDs back-referenced by tasks - validator rules, RBAC matrix, query-builder SQL shapes, cursor round-trips, cache hit/miss paths, observability metrics, frontend component behaviors. Triggers - "write unit tests for task.
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
custom-models
How to configure custom or unlisted models for any provider.
using-agents
Understanding and using different agents in Kilo Code.
code-reviewer
Use this agent when you need a senior software engineer's perspective on code quality, focusing on simplification, minimalism, and elegance. This agent should be invoked after writing or modifying code to ensure it follows best practices and is as clean as possible. Examples:\n\n \nContext: The user has just written a…