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/KimYx0207/Meta_KimWrote 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/kimyx0207/meta_kim/meta-choice-surface)<a href="https://agentmods.dev/rules/kimyx0207/meta_kim/meta-choice-surface"><img src="https://agentmods.dev/badge/rules/kimyx0207/meta_kim/meta-choice-surface.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 5.1 | $0.00520 | $0.00520 |
| Opus 5 | $0.00260 | $0.00260 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
meta-choice-surface 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 7d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta_Kim Choice Surface (Cursor)
When meta-theory is active in Cursor and a user decision would change route,
scope, risk, acceptance, owner, permission, or non-goal, use this stable
choice-surface route:
- Finish Critical/Fetch/Thinking evidence first when the decision is not a Critical blocker.
- Render a short localized chat decision card with 2-4 meaningful options and one recommended default.
- Stop and wait for the user's explicit reply before Execution.
- Record the choice surface as
conversation_fallbackunless a real Cursor-native question surface is exposed in the active host.
Do not call this a popup. Do not claim Cursor displayed a native modal. Cursor
preToolUse hooks are for hard tool-call governance, and beforeSubmitPrompt
hooks are for prompt-time adapters; neither is a verified arbitrary
multi-option question UI for Meta_Kim.
Stable Cursor trigger
alwaysApply: trueloads this rule on every Cursor prompt..cursor/hooks.jsonregisterspreToolUsewithfailClosed: truefor mechanical execution gating..cursor/hooks.jsonmay registerbeforeSubmitPromptadapters for memory or prompt enhancement, but Meta_Kim must not depend on that event as the only user-choice surface.
Decision Card Shape
Use the user's language. Keep the card compact:
- AI understanding: one sentence.
- Recommended option: label it clearly.
- Options: 2-4 options, each with the trade-off.
- Wait state: ask the user to choose before continuing.
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.
- 7d ago First seen · 55 lines · 520 tokens per session scan A 757e4dcae865
meta-choice-surface is a cursor rule published in the GitHub repository KimYx0207/Meta_Kim (269 stars, last pushed 2d ago), licensed Apache-2.0. It adds 520 tokens to every session, about $0.0026 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
language-agnostic-patterns
Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.
cursor-tools-mastery
Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.
cursor-agent-orchestration
Cursor 3.7 orchestration guide: when to plan, when to delegate, nested subagents, multi-environment handoffs, /best-of-n, and Await for long-running branches.
fable5-reasoning
Fable 5 reasoning protocols: task interpretation, risk-first decomposition, approach selection, interleaved thinking, hypothesis ledgers, premortems, calibration, and the stuck-strategy ladder. Load for complex, ambiguous, or long-horizon tasks, for debugging strategy, or whenever progress stalls.
cursor-mcp-optimization
Cursor 3.7 MCP optimization: browser Design Mode, canvases, Figma, Cloudflare tools, MCP Apps structured content, and direct action patterns.
minimax-mcp-tools
MCP and web-tool guidance: current-doc retrieval, direct-tool preference, MCP Apps structured content, and version-aware external lookups.