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-enforcement)<a href="https://agentmods.dev/rules/kimyx0207/meta_kim/meta-enforcement"><img src="https://agentmods.dev/badge/rules/kimyx0207/meta_kim/meta-enforcement.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 | $0.01135 | $0.01135 |
| Opus 5 | $0.00567 | $0.00567 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
meta-enforcement 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta-Agent Execution Boundary (Cursor Declarative Backup)
Cursor's official Hooks surface does expose a real tool-call deny protocol via preToolUse
hooks, equivalent in effect to Claude Code's
hookSpecificOutput.permissionDecision: "deny". A hook can deny a tool call
by either:
- exiting with code
2and writing a deny reason to stderr, or - emitting stdout JSON
{"permission": "deny", "user_message": "...", "agent_message": "..."}
When combined with failClosed: true, hook crashes default to deny rather
than allow. The canonical mechanical enforcement now lives in
.cursor/hooks/enforce-agent-dispatch.mjs (synced from
canonical/runtime-assets/cursor/hooks/). See
Cursor Hooks docs for the wire protocol.
This MDC rule is the declarative backup. It applies on every prompt
(alwaysApply: true) and keeps the meta-agent boundary intact when the
hook is misconfigured, disabled, unavailable in the active host, or otherwise
unavailable. Hook-first, MDC-as-safety-net.
Hard rules (apply at every turn)
-
The nine meta-agents are governance-only. Names:
meta-warden,meta-conductor,meta-genesis,meta-artisan,meta-sentinel,meta-librarian,meta-prism,meta-scout,meta-chrysalis. Each one carriesexecutionBlock=truein its canonical definition. -
Meta-agents do NOT touch execution tools. If the user requests a meta-agent to write code, run tests, edit files, debug, build, or perform any direct execution task, refuse and instead:
- state which meta-agent boundary the request violates
- recommend the correct execution-layer agent (or open a
capabilityGapPacketif no owner exists) - hand the actual work to that agent via Cursor's native agent invocation
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 · 104 lines · 1,135 tokens per session scan A 2bb67b35d757
meta-enforcement is a cursor rule published in the GitHub repository KimYx0207/Meta_Kim (270 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,135 tokens to every session, about $0.0057 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
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.
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-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.
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.
reqforge-dev-build
Dev Builder — implementation execution. Build code phase by phase following DEV-PLAN, each Task goes through review → fix loop.