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/rules/perniemann/pncore/pn-orchestrator-lead)<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.
<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>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 | $0.00661 | $0.00661 |
| Opus 5 | $0.00331 | $0.00331 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
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.
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_horizon → lead; 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
- Read
subagentTierHintsandtasks[].suggestedSubagentTieron the response. - For each parallel task, spawn Task (
generalPurpose,best-of-n-runner,explore,shell) withmodelset to the builder or explorer exemplar from hints — not the lead model. - Call
suggest_model_tierwithrole: "orchestrator"at session start for the recommended long-horizon exemplar (default: Fable; alternates inTIER_META). - Re-call
workflow_steponly after all delegated tasks report summaries intaskResults. - After two verification failures on the same finding, record in loop STATE and follow
pn-core://reference/loop-catalog/escalation-queue.md.
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.
- 8d ago First seen · 39 lines · 661 tokens per session scan A cbd36f022fbb
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.
Other cursor rules, from other repositories
t-800-mandatory-routing
A mandatory routing rule for creating or changing subagents, skills, commands, rules, and hooks. Hooks are scripts that run automatically when certain events occur.
t-800-operator-routing
A routing rule for explaining Cursor and its agent features to Russian-speaking beginners. Cursor is a code editor with built-in AI assistance.
t-800-factory-routing
A routing rule for building and coordinating groups of coding subagents. Subagents are separate agents that handle parts of a larger task.
t-800-cloud-hub-routing
A routing rule for Cloud Hub setup work, sending matching requests to a designated lead agent. Cloud Hub is the project area named in the rule.
typescript-conventions
Cursor rule "typescript-conventions" from VirtusLab-Open-Source/strapi-plugin-mcp, covering typescript and coding conventions, typescript configuration, import/export patterns, code organization and services (server/src/services/).
1001-typescript
APPLY TypeScript best practices WHEN writing code TO ensure type safety, readability, and maintainability.