What is pn-build-gate?

A set of rules that controls how build and design requests are planned before implementation. It requires discovery and plan review, and says decisions needing user input must be confirmed first.

Use it for build, design, or scaffolding work that needs discovery, a plan, a challenge of that plan, and confirmation before implementation.

It prevents coding from starting with missing requirements or unapproved choices, which can lead to rework.

pn-build-gate — Cursor rule for coding agents by perniemann: A set of rules that controls how build and…

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 rules/perniemann/pncore/pn-build-gate

Clone the repo

git clone --depth 1 https://github.com/perniemann/pnCore

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/perniemann/pncore/pn-build-gate.svg)](https://agentmods.dev/rules/perniemann/pncore/pn-build-gate)

Your own site

<a href="https://agentmods.dev/rules/perniemann/pncore/pn-build-gate"><img src="https://agentmods.dev/badge/rules/perniemann/pncore/pn-build-gate.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,736 This file is loaded in full into every session.

When invoked 1,736 The same file — it is already loaded in full.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.01736	$0.01736
Opus 5	$0.00868	$0.00868
Sonnet 5	$0.00347	$0.00347
Haiku 4.5	$0.00174	$0.00174

Measured 4d ago against content hash 69618e909bf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

pn-build-gate 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 4d 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.

packages/pn-core-mcp/content/rules/pn-build-gate.mdc · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build gate

Discovery and skeptic must run for build/design work. Use the full flow; do not go directly to implementation.

Plan accuracy (all workflows)

Whenever a plan would contain options or decisions that need user input, ask before finalizing. Use ask_question when available; otherwise call workflow_confirm and stop until the user replies. Do not infer or assume choices. Do not use free-text-only gates (e.g. "Reply yes") when structured options exist — see pn-core://reference/conventions.md (Skeptic gate).

After pn-skeptic-challenge or /pn-skeptic, the turn must end with AskQuestion or workflow_confirm (gate_type: "skeptic"), not plaintext confirmation.

For the full command routing table (pn-new, pn-setup, workflow_step vs get_command, etc.) see pn-core://reference/RUNBOOK.md.

Command-contract acknowledgement (no silent re-route)

When a /pn-* command is invoked but the user's actual request does not match that command's contract, state the mismatch in plain prose in the first response before doing anything else:

"You invoked /X but the ask is Y; I'll re-route to Z unless you'd rather I run X as written."

Silent re-routing is a RULE-MISS (candidate code COMMAND-MISMATCH per pn-session-retro; see § Command-contract acknowledgement above). The mandatory [pn-command] ▲ start marker still applies — never drop it during a re-route.

Build/design intent (full flow required)

When the user requests to build, design, scaffold, add feature, new project, or create (component, page, app, plugin):

Exclusion: Image/SVG creation → get_command("pn-assets"). Do not route to pn-new or workflow_step for these.

Condition	Action
User says "onboard" or "analyze codebase"	`get_command("pn-setup")`
Existing project code + no `project-context.mdc` + add/refactor/extend request	Ask: "Run pn-setup to create project context first?" Yes → `get_command("pn-setup")`; No → treat as new project
New project, no `docs/refs/PRD.md`, no `.ref/`	Ask: "No docs found. Create project doc set first?" Yes → `workflow_step("project_kickoff", 0, {})` or `get_command("pn-new")` Involved; No → `get_command("pn-new")`
`project-context.mdc` + plan exist, design-only	`workflow_step("design", 0, { request })` or `get_command("pn-design")`
`project-context.mdc` + plan exist, full-stack	`workflow_step("full_dev", 0, { request, intent? })` or `get_command("pn-build")`

Read the full file on GitHub · 94 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.

4d ago First seen · 94 lines · 1,736 tokens per session scan A 69618e909bf5

Subscribe to this mod's changes

pn-build-gate is a cursor rule published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 1,736 tokens to every session, about $0.0087 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.

LLM Writing and docs agents cursor mcp plugin

t-800-mandatory-routing

ОБЯЗАТЕЛЬНО: создание и правка субагентов, skills, commands, rules, hooks — только через T-800 Agent (цех Skynet). Сначала intake? + scout + research DEEP + brain-lead, затем t-800-factory. Не собирать артефакты ad-hoc в main chat.

Khar-AG/t-800-agent · 1,682 tokens

t-800-operator-routing

Маршрутизация к T-800 Operator для русскоязычных новичков: первый запуск Cursor, вопросы про Agent/Ask/Plan/Debug, rules, skills, MCP, автоматизацию, просьбы объяснить «на пальцах». Делегируй Task(t-800-operator), не дублируй длинные объяснения в основном чате.

Khar-AG/t-800-agent · 76 tokens

t-800-factory-routing

Маршрутизация к T-800 Factory: создание субагентов, проектирование плагина, интеграция агентов, реестр, граф связей, масштабирование 100+ agents. Делегируй Task(t-800-factory), не создавай агентов ad-hoc в main chat.

Khar-AG/t-800-agent · 65 tokens

t-800-knowledge-refresh

Обновление базы знаний T-800: когда появились новые функции Cursor, устарел manifest (>30 дней), есть UPDATE-QUEUE.md с pending, пользователь спрашивает про фичу которой нет в KB, или после changelog Cursor. В проекте Cursor Junior делегируй обслуживание Task(t-800-maintainer).

Khar-AG/t-800-agent · 0 tokens

t-800-cloud-hub-routing

Маршрутизация Cloud Hub Automation Setup: при /t800-cloud-hub, /t800-hub-setup или правках /cloud-hub/ → Task(t-800-cloud-hub-lead). Не always-on.