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/mission69b/t2000/spend-lanesgit clone --depth 1 https://github.com/mission69b/t2000Wrote 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/mission69b/t2000/spend-lanes)<a href="https://agentmods.dev/rules/mission69b/t2000/spend-lanes"><img src="https://agentmods.dev/badge/rules/mission69b/t2000/spend-lanes.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 | $0.00601 | $0.00601 |
| Opus 5 | $0.00300 | $0.00300 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
spend-lanes 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spend lanes (founder 2026-07-24, revised)
Burning Cursor frontier tokens (especially claude-fable-*-thinking-high) on
implementation is the failure mode this rule stops. Founder pays Cursor Max +
Anthropic Max; all multi-file code work goes to Claude Code on the Max
subscription (browser OAuth login — never an Anthropic API key in Cursor).
The two lanes
| Lane | Tool | Use for |
|---|---|---|
| Think / Review | This Cursor chat (default = Auto; Fable only for hard architecture or debugging) | Specs, plans, diff review, acceptance criteria, handoff prompts |
| Build | Claude Code (claude) on Anthropic Max |
Features, refactors, multi-file implementation, long agentic loops, mechanical sweeps |
What this chat MUST do
When the user asks for code / implementation / "build X" / "fix the tests":
- Write a short plan + acceptance criteria (verifiable).
- Emit a paste-ready Claude Code prompt (Build lane).
- Stop. Do not open a large edit loop in Cursor.
Exceptions (OK to implement here): single-file typo, one-line config, or the user explicitly says "do it in this chat."
What this chat MUST NOT do
- Multi-hour agentic coding sessions in Cursor on Fable / thinking-high.
- Re-open or continue a months-long mega-thread for a new task — one task = one chat.
- Put an Anthropic API key into Cursor "to use Max" — Max does not cover API keys.
Where the rules actually live (2026-07-24 migration)
Claude Code is now the canonical agent surface. .claude/ owns the content:
CLAUDE.md— auto-loaded every turn (architecture, critical rules, release process).claude/skills/*/SKILL.md— subsystem depth, auto-loaded on task match.claude/commands/*.md— the repeatable rituals (/release,/ship,/tracker)
Files in .cursor/rules/ are pointers into .claude/, not copies — so the two
tools cannot drift. When a rule needs updating, edit the .claude/ file. The one
deliberate exception is engineering-discipline.mdc, which mirrors the short
always-on block from CLAUDE.md because Cursor does not read CLAUDE.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.
- 4d ago First seen · 54 lines · 601 tokens per session scan A 38975323f9d0
spend-lanes is a cursor rule published in the GitHub repository mission69b/t2000 (23 stars, last pushed 2d ago), licensed MIT. It adds 601 tokens to every session, about $0.0030 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.
Other cursor rules, from other repositories
selat
SELAT capability layer — reach for SELAT before saying you can't do something or sending the user to an external tool / API key.
cursorrules
You have a CardZero payment wallet on Base (Coinbase L2) for making USDC payments.
vaaya
Vaaya — consult-first rule for any capability gap.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.