cursor

cursor is a cursor rule for coding agents from l6e-ai/l6e-mcp. It costs 2,154 tokens per session, scanned B, a copy of l6e-budget-enforcement, MIT.

A set of Cursor rules for controlling calls to l6e, an external service used through MCP tools. It specifies how to identify the model and client, and which parameters each call accepts.

In plain words
What is it for?
Use it when running l6e from Cursor’s Plan or Agent mode, especially when starting or ending sessions, checking budget approval, or coordinating sub-agents.
Why use it?
It helps prevent invalid tool requests, billing mistakes, and l6e calls made through unsupported code paths.

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/l6e-ai/l6e-mcp/cursor
Clone the repo
git clone --depth 1 https://github.com/l6e-ai/l6e-mcp

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

README.md
[![agentmods](https://agentmods.dev/badge/rules/l6e-ai/l6e-mcp/cursor.svg)](https://agentmods.dev/rules/l6e-ai/l6e-mcp/cursor)
Your own site
<a href="https://agentmods.dev/rules/l6e-ai/l6e-mcp/cursor"><img src="https://agentmods.dev/badge/rules/l6e-ai/l6e-mcp/cursor.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,154 This file is loaded in full into every session.
When invoked 2,154 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.02154 $0.02154
Opus 5 $0.01077 $0.01077
Sonnet 5 $0.00431 $0.00431
Haiku 4.5 $0.00215 $0.00215

Measured 3d ago against content hash a851224ef187, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

cursor scanned grade B with 1 finding 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 3d 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.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

- Never tell the user how much they spent when costs are calibrated (not reconciled).
Origin

This is a copy

100% identical to l6e-budget-enforcement — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

src/l6e_mcp/rules/cursor.mdc · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

l6e budget enforcement

Use l6e only via MCP tools. Never import l6e or l6e_mcp in Python. Pass model as your billing model ID — see "Model identification" below to derive it from your system prompt (or pass "unknown"). Set client to "cursor". USE IN PLAN OR AGENT MODE.

Always call MCP tools with only the parameters defined in the tool schema. Never invent parameters — additionalProperties: false means any extra field causes a hard validation error. When in doubt, read the schema descriptor before calling.

  • l6e_run_start: accepts budget_usd, model, client, task_summary (brief label, okay to omit), parent_session_id (for multi-session orchestration), and optional config fields. Do NOT pass session_id or task_description.
  • l6e_run_end: accepts session_id and optional task_summary (brief label of what was done).
  • l6e_authorize_call: budget gate and status check. Pass at every stage boundary and before sub-agents. Returns allow, reroute, or halt. Pass check_only=True for lightweight mid-stage pressure checks. Accepts optional model to override the session model for a specific call (see Multi-model sessions below).
  • l6e_record_usage: do NOT call unless you have real token-usage data from the client runtime. This tool is for exact accounting only.
  • Never tell the user how much they spent when costs are calibrated (not reconciled).

Checkpoint policy

All budget checks use l6e_authorize_call. Pass check_only=True for lightweight pressure checks (no call record, no gate decision). Omit check_only (or pass False) for full gate checks that return allow/reroute/halt and record a call.

Sub-agent gate (blocking prerequisite): You MUST call l6e_authorize_call with actor_type="subagent" and obtain an allow response BEFORE launching any Task sub-agent. Do not launch the sub-agent, do not write its prompt, do not call the Task tool until you have a call_id from this check. There are no exceptions — budget size, perceived task cheapness, and tool type are all irrelevant.

Read the full file on GitHub · 104 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. 3d ago First seen · 104 lines · 2,154 tokens per session scan B a851224ef187

Subscribe to this mod's changes

cursor is a cursor rule published in the GitHub repository l6e-ai/l6e-mcp (4 stars, last pushed 4mo ago), licensed MIT. It adds 2,154 tokens to every session, about $0.0108 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). It is 100% identical to l6e-budget-enforcement, differing in 0 lines, and is treated as a copy.