cursor-starter

cursor-starter is a cursor rule for coding agents from blackzhanzhan/Cyber-Ming-Protocol. It costs 421 tokens per session, scanned A, original, MIT.

A repository governance rule for the Cyber-Ming protocol, which sets procedures for understanding project state and planning code changes before editing.

In plain words
What is it for?
It helps guide takeover sessions, initialize or read project records, route planning through available contracts, and control when unrestricted development is allowed.
Why use it?
It reduces the risk of changing code without knowing the repository’s current architecture, data model, or recorded state.

Cursor rule

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/blackzhanzhan/cyber-ming-protocol/cursor-starter
Clone the repo
git clone --depth 1 https://github.com/blackzhanzhan/Cyber-Ming-Protocol

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 cursor-starter

README.md
[![agentmods](https://agentmods.dev/badge/rules/blackzhanzhan/cyber-ming-protocol/cursor-starter.svg)](https://agentmods.dev/rules/blackzhanzhan/cyber-ming-protocol/cursor-starter)
Your own site
<a href="https://agentmods.dev/rules/blackzhanzhan/cyber-ming-protocol/cursor-starter"><img src="https://agentmods.dev/badge/rules/blackzhanzhan/cyber-ming-protocol/cursor-starter.svg" alt="Measured on agentmods" height="20"></a>
Per session 421 This file is loaded in full into every session.
When invoked 421 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.

ModelPer sessionOnce invoked
Fable 5 $0.00421 $0.00421
Opus 5 $0.00211 $0.00211
Sonnet 5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 4d ago against content hash 4134311209c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-starter 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.

starter/cursor-starter.mdc · 38 lines

What it actually says

Cyber-Ming Starter

This workspace uses Cyber-Ming-Protocol.

  • Bootstrap under repository law before editing.
  • Default to contract development before code changes.
  • Route planning through contract-hook-router when the skill is available.
  • Enter free development mode / 自由开发模式 only when the user explicitly activates it.
  • Keep Cyber-Ming's sovereign/imperial narrative available as style, while keeping operational instructions readable in the user's language.
  • If dev_repo/state.json, journal.jsonl, evidence_index.json, or tree.md exist, treat them as current runtime truth.
  • If dev_repo/architecture/ exists, treat it as current architecture truth before planning broad changes.
  • If dev_repo/architecture/data-model/ exists, treat it as current data-model truth before planning durable data, schema, migration, or persistence changes.
  • In fresh or takeover sessions, reconstruct state and initialize/read architecture truth before edits.
  • Treat host plan/ask modes as plan-start hook surfaces only. Compile plans into Cyber-Ming contracts before execution.
  • If a change alters architecture boundaries, responsibilities, dependencies, runtime flows, or invariants, use an architecture amendment contract rather than a normal implementation contract.
  • If a change alters entities, relationships, identity, cardinality, source/derived status, migrations, backfills, or persistence semantics, use an ER/data-model amendment contract rather than a normal implementation contract.

Recommended first prompt:

{{FIRST_PROMPT}}

Reference docs live at:

  • {{DOCS_ROOT}}/BOOTSTRAP.md
  • {{DOCS_ROOT}}/bootstrap/ide-executor.md
  • {{DOCS_ROOT}}/bootstrap/web-auditor.md
  • {{DOCS_ROOT}}/dev_repo-runtime.md
  • {{DOCS_ROOT}}/architecture/README.md
  • {{DOCS_ROOT}}/architecture/data-model/README.md
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. 4d ago First seen · 38 lines · 421 tokens per session scan A 4134311209c8

Subscribe to this mod's changes

cursor-starter is a cursor rule published in the GitHub repository blackzhanzhan/Cyber-Ming-Protocol (56 stars, last pushed 3mo ago), licensed MIT. It adds 421 tokens to every session, about $0.0021 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 2026-08-30.