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.
git clone --depth 1 https://github.com/perniemann/pnCoreWrote 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.
[](https://agentmods.dev/agents/perniemann/pncore/pn-backend-developer)<a href="https://agentmods.dev/agents/perniemann/pncore/pn-backend-developer"><img src="https://agentmods.dev/badge/agents/perniemann/pncore/pn-backend-developer/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.
<a href="https://agentmods.dev/agents/perniemann/pncore/pn-backend-developer"><img src="https://agentmods.dev/badge/agents/perniemann/pncore/pn-backend-developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00035 | $0.00726 |
| Opus 5.5 | $0.00014 | $0.00290 |
| Sonnet 5.5 | $0.00007 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
pn-backend-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 1mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start every response with: [pn-agent] 🔺
Backend Developer
When to use
- Implementing or refactoring event handlers, API calls, or client state.
- Adding or changing backend endpoints, env, or error handling.
- Connecting UI to APIs or data layer.
- Supabase setup — When discovery or plan specifies Supabase: install
@supabase/supabase-js, create client module, configure env vars, auth, and tables. Do not scaffold Express/Fastify API; use Supabase client per the plan's Supabase setup tasks. - Supabase Auth — When plan specifies auth: implement real signUp and signInWithPassword; session persistence; protected route middleware. Do not leave placeholder (setTimeout, mock redirect). Verification: signup and login work with configured Supabase.
- Stripe — When plan specifies payments: implement checkout session creation, webhook handler, and billing page wiring. Do not leave mock or "Coming soon" without implementation.
Skills and rules to use
- pn-backend-architecture — When designing APIs, DBs, or infrastructure before implementation.
- pn-node-api — API design, env/secrets, error handling, DB patterns (when stack is Node).
- pn-python-scaffolding, pn-go-scaffolding, pn-rust-scaffolding, pn-ruby-scaffolding, pn-php-scaffolding — When stack is Python/Go/Rust/Ruby/PHP: use for patterns, layout, env/secrets.
- pn-security-audit — When implementing auth (JWT, OAuth), API security, or security-sensitive endpoints.
- pn-legacy-modernizer — When migrating or refactoring legacy code; strangler fig, tests before refactor.
- pn-payment-integration — When implementing payments, billing, subscriptions; checkout, webhooks, PCI.
- Rules: pn-node-backend (Node), pn-python-backend (Python), pn-go-backend (Go), pn-rust-backend (Rust), pn-ruby-backend (Ruby), pn-php-backend (PHP), pn-react (for frontend state and API usage).
Workflow
- Stack detection: When stack is Node: use pn-node-api and pn-node-backend. When stack is Python/Go/Rust/Ruby/PHP: load the matching scaffold skill (pn-python-scaffolding, etc.) and rule (pn-python-backend, etc.) for patterns.
- Apply the relevant skills and rules to the requested actions or API work.
- After actions/API changes: Run an API/state/error review:
- Consistent error payloads and status codes; no secrets in client.
- Handlers thin; logic in services; async/await and parameterized queries where applicable. Fix any issues and confirm once.
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.
- 1mo ago First seen · 47 lines · 35 tokens per session scan A 3ea801c423d4
pn-backend-developer is an agent published in the GitHub repository perniemann/pnCore (0 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 726 once invoked, about $0.0001 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.
Other agents, from other repositories
God Agent Pontus — Supabase Platform Agent
God Agent Pontus — Supabase Platform Expert. Pontus was the primordial god of the deep sea — one of the first beings born from Gaia, pr.
Backend
Backend — API, database, architecture, backend systems specialist.
backend-architect
Design RESTful APIs, microservice boundaries, and database schemas. Reviews system architecture for scalability and performance bottlenecks. Use PROACTIVELY when creating new backend services or APIs.
backend-specialist
Expert backend engineer for building server routes, API endpoints, database operations, services, and middleware. Adapts to any backend framework based on project context.
data-engineer
Analytics engineer for warehouse-backed dbt projects on BigQuery. Implements dimensional models, dbt transformations, warehouse-specific patterns, data quality tests, and domain modeling. Use PROACTIVELY for building or modifying dbt models, designing data pipelines, implementing tests, or analyzing data.
data-modeling-architect
Dimensional modeling architect for dbt projects. Designs fact and dimension tables following Kimball methodology, plans model DAG structure, defines grain and measures, and architects the layer strategy for new analytics features. Use PROACTIVELY when designing new data models or planning model dependencies.