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 rules/perniemann/pncore/pn-mcp-proactivegit 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/rules/perniemann/pncore/pn-mcp-proactive)<a href="https://agentmods.dev/rules/perniemann/pncore/pn-mcp-proactive"><img src="https://agentmods.dev/badge/rules/perniemann/pncore/pn-mcp-proactive.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 5.1 | $0.01111 | $0.01111 |
| Opus 5 | $0.00556 | $0.00556 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
pn-mcp-proactive 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 5d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pn-core MCP: Proactive Skill Use
When pn-core MCP is available and the user's task clearly matches a pn skill or agent, use the MCP tools to load and follow that content.
Discovery: Use list_skills or list_agents when unsure which id applies. Use get_skill, get_agent, get_command, or get_rule to load full content. Call list_workflow_types when the user asks "what workflows are available?"
Session start: When pn-core MCP is available, call project_context (default mode: "agent") once at the start of a coding session to load the cold-session packet (context-index artifacts, resume line, attested drift, recent handoff/run-events trail). Do not rely on Cursor sessionStart hook inject for this packet.
Quick map (common intents):
| User intent | pn-core id |
|---|---|
| Today's date (changelog, "as of", copyright) | health → use calendarDateUtc / timestampUtc |
| Session start / resume / what is drifted | project_context (mode: "agent" default; operator for counts) |
| New project or feature, kickoff | get_command("pn-new") |
| Configure / onboard existing project | get_command("pn-setup") |
| Full dev loop, multi-step feature | workflow_step("full_dev", 0, {}) |
| New project or feature, discovery | pn-discovery-questionnaire |
| Review code quality | get_command("pn-review") or get_skill("pn-review-optimize-loop") |
| Plan before coding | pn-writing-plans |
| Stress-test a plan | get_command("pn-grill") |
| Pressure-test a startup idea | get_command("pn-pressure-test") or get_skill("pn-pressure-test") |
| Strict verification + delivery pack | get_command("pn-deliver") |
| Create image or SVG | get_command("pn-assets") |
| Architecture, flowchart, sequence, state, flywheel, 2×2, layers, swimlane, data-flow, org-chart | get_command("pn-diagram") or get_skill("pn-diagram-design") |
| Targeted visual change (one area, not full redesign) | get_command("pn-visual-tweak") or workflow_step("visual_tweak", …) |
| Distinctive UI baseline (always-apply rule + checklist) | get_rule("pn-aesthetics-baseline") or pn-core://reference/aesthetics-baseline.md |
| Static HTML preview (save + open browser) | get_skill("pn-html-preview") |
| ComfyUI, T2I/T2V pipelines, cinematic prompting, lighting | get_agent("pn-generative-media-director") — or narrow: pn-comfyui-workflows, pn-generative-video-pipelines, pn-cinematography-lighting |
| Prior art / existing solutions | pn-prior-art-research |
| Code trace, find definition, who calls X | Octocode tools when available |
| UE MCP server selection (which server to use) | get_skill("pn-unreal-mcp") |
| Unreal Engine development (C++, BP, assets, Python) | get_skill("pn-unreal-dev") |
| Unreal editor automation (spawn actors, compile BP, edit materials) | unreal-mcp tools when available |
| Blender scripting, add-ons, export pipelines, Geometry Nodes | get_skill("pn-blender-scripting") |
| Blender live session control (mesh ops, scene analysis, rename data-blocks) | blender MCP tools when available |
| Godot MCP server selection (which server to use) | get_skill("pn-godot-mcp") |
| Godot Engine development (GDScript, GDExtension, shaders, multiplayer) | get_skill("pn-godot-dev") |
| Godot live editor / project automation (run, scene edit, capture errors) | godot MCP tools when available |
Full routing table (all skills, agents, workflows, companion MCPs): pn-core://reference/RUNBOOK.md
When the user names a skill (e.g. "use pn-discovery-questionnaire"), call get_skill immediately. For design with philosophy alignment, prefer get_command("pn-design").
Octocode: Preferred for prior-art and code archaeology. Use its tools for code search, LSP navigation, and GitHub research when available.
Companion MCPs: When present, combine with pn skills — Stripe MCP + pn-payment-integration; n8n MCP + pn-n8n-patterns; shadcn MCP for component install; Playwright MCP + pn-smoke-tests; unreal-mcp + pn-unreal-dev; blender MCP + pn-blender-scripting; godot MCP + pn-godot-dev.
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.
- 5d ago First seen · 53 lines · 1,111 tokens per session scan A e853f9435eca
pn-mcp-proactive is a cursor rule published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 1,111 tokens to every session, about $0.0056 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 cursor rules, from other repositories
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.
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.
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.
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).
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.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.