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 commands/perniemann/pncore/pngit 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/commands/perniemann/pncore/pn)<a href="https://agentmods.dev/commands/perniemann/pncore/pn"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.00547 |
| Opus 5 | $0.00023 | $0.00273 |
| Sonnet 5 | $0.00009 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
pn 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 3d 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.
What it actually says
pn
Start every response with: [pn-command] 🔺
Orientation router for the pnCore command palette. In Cursor IDE, type / and open the pn submenu for all commands. On Cursor CLI or pi.dev, use this stub or MCP get_command / get_skill.
Step 1 — Pick a track
Use ask_question when available:
- Start — new project, setup, or guide (
pn-new,pn-setup,pn-guide) - Build — full dev, program, deliver (
pn-build,pn-program,pn-best-of-n,pn-deliver) - Design — UI build, variants, polish, assets (
pn-design,pn-visual-tweak,pn-polish, …) - Product management — PRD, stories, strategy (
pn-create-prd,pn-user-stories,pn-strategy, …) - Audit — frontend or backend quality (
pn-frontend-audit,pn-backend-audit) - Challenge — plan stress-test (
pn-grill,pn-skeptic,pn-prompt-optimize) - Ship — review, handoff, retro, video lint (
pn-review,pn-handoff,pn-retro,pn-video-lint) - Show full map — load
get_command("pn-guide")
Step 2 — Run
Load the chosen command via get_command("<id>") and follow its contract.
Platform notes
| Platform | How to reach commands |
|---|---|
| Cursor IDE | / → pn submenu → pick leaf (e.g. pn-build) |
| Cursor CLI | This /pn stub or get_command("<id>") — nested submenu not available |
| pi.dev | /pn opens the pnCore command menu (like /model); pick a workflow from the selector. Direct: /pn pn-build |
Guardrails
- Do not block on this router when the user already named a command — run that command directly.
- Technical plan review →
pn-skepticorpn-grill, notpn-pressure-test.
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.
- 3d ago First seen · 41 lines · 47 tokens per session scan A 856a3312644c
pn is a command published in the GitHub repository perniemann/pnCore (0 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 547 once invoked, about $0.0002 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 commands, from other repositories
cleanup
Autonomous cleanup-loop iteration: discover ONE target → complete execution → verify → report. Runs stateless: derive from current tree; assume prior runs left it consistent.
learn
Command "learn" from chohra-med/expo_boilerplate, covering command: learn — the learning loop (feedback → rules), when to run it, invocation, the loop (6 steps) and 1 — capture.
migrate
Command "migrate" from chohra-med/expo_boilerplate, covering invocation, steps and rule.
netllm-setup
First-time netllm install from this repo (uv sync, init, discover, verify).
react-router-client-loader
Do this in a clientLoader and use loaderData to render the component. DO NOT create mock data, new interfaces, or mock data loader functions. Instead, assume loaderData has all of the data you need to render the component.
t-800-sync
Запусти ручной sync официальной документации Cursor.