pn-orchestrator-lead

pn-orchestrator-lead is a cursor rule for Cursor from perniemann/pnCore. It costs 661 tokens per session, scanned A, original, MIT.

A set of rules for leading multi-step coding workflows and deciding when work should be delegated to other coding agents.

In plain words
What is it for?
Use it when coordinating parallel work, selecting an agent model tier, passing workflow state, and managing delegated tasks.
Why use it?
It makes delegation choices explicit and keeps planning, coordination, implementation, and verification responsibilities clear.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: mentions subagents.

Good fit Use it when coordinating parallel work, selecting an agent model tier, passing workflow state, and managing delegated tasks.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/perniemann/pncore/pn-orchestrator-lead
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.

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

Made for: Cursor.

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.

agentmods badge for pn-orchestrator-lead

README.md
[![agentmods](https://agentmods.dev/badge/rules/perniemann/pncore/pn-orchestrator-lead/github.svg)](https://agentmods.dev/rules/perniemann/pncore/pn-orchestrator-lead)
Your own site
<a href="https://agentmods.dev/rules/perniemann/pncore/pn-orchestrator-lead"><img src="https://agentmods.dev/badge/rules/perniemann/pncore/pn-orchestrator-lead/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.

agentmods 80×15 button for pn-orchestrator-lead

Your own site · 80×15
<a href="https://agentmods.dev/rules/perniemann/pncore/pn-orchestrator-lead"><img src="https://agentmods.dev/badge/rules/perniemann/pncore/pn-orchestrator-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 661 This file is loaded in full into every session.
When invoked 661 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00661 $0.00661
Opus 5 $0.00331 $0.00331
Sonnet 5 $0.00132 $0.00132
Haiku 4.5 $0.00066 $0.00066

Measured 8d ago against content hash cbd36f022fbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pn-orchestrator-lead 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 8d 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-orchestrator-lead.mdc · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator lead (model-tier delegation)

When driving workflow_step as the lead session, pass your active model tier in state so pnCore can adapt orchestration vs implementation:

State key Type Role
leadModelTier fast | standard | premium | premium_thinking | long_horizon Preferred — declare the tier matching your picker model
sessionModel string Optional picker slug; resolved via exemplars/alternates from suggest_model_tier / pn-core://reference/subagent-routing.md
orchestrationIntent boolean Opt-in delegation before parallel fan-out: long_horizonlead; premium → light_delegate; standard + parallel → light_delegate

Echo these on every workflow_step call in the same run (with run_id). Full delegation contracts appear when parallel: true or orchestrationIntent: true (including non-parallel steps when intent is set).

When workflow_step returns orchestrationMode

Mode Lead behavior
lead long_horizon declared — plan, coordinate, verify only; no bulk file edits in lead session
light_delegate Premium + (parallel or orchestrationIntent), or orchestrationIntent + parallel on standard — spawn Task subagents per tasks[]; lead may fix ≤1 trivial file
implementer Default — lead may implement directly

Delegation contract

  1. Read subagentTierHints and tasks[].suggestedSubagentTier on the response.
  2. For each parallel task, spawn Task (generalPurpose, best-of-n-runner, explore, shell) with model set to the builder or explorer exemplar from hints — not the lead model.
  3. Call suggest_model_tier with role: "orchestrator" at session start for the recommended long-horizon exemplar (default: Fable; alternates in TIER_META).
  4. Re-call workflow_step only after all delegated tasks report summaries in taskResults.
  5. After two verification failures on the same finding, record in loop STATE and follow pn-core://reference/loop-catalog/escalation-queue.md.

Read the full file on GitHub · 39 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.

  1. 8d ago First seen · 39 lines · 661 tokens per session scan A cbd36f022fbb

Subscribe to this mod's changes

pn-orchestrator-lead is a cursor rule published in the GitHub repository perniemann/pnCore (0 stars, last pushed 3d ago), licensed MIT. It adds 661 tokens to every session, about $0.0033 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.