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-theory-dispatch)<a href="https://agentmods.dev/rules/kimyx0207/meta_kim/meta-theory-dispatch"><img src="https://agentmods.dev/badge/rules/kimyx0207/meta_kim/meta-theory-dispatch.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 | $0.00776 | $0.00776 |
| Opus 5 | $0.00388 | $0.00388 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
meta-theory-dispatch 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta-Theory Dispatch (Cursor)
This repository treats ordinary durable natural-language work as the entry
surface for Meta_Kim governance. In Cursor, the stable entry is this rule plus
the project hooks in .cursor/hooks.json; do not wait for a Claude/Codex slash
command file to appear.
Mandatory Entry Cases
Use the governed Meta_Kim route when the prompt contains any of these shapes:
- explicit
meta-theory,/meta-theory,元理论,critical and fetch thinking and review - project / repo / codebase understanding, for example "what is this project", "这个项目干啥", "这个项目怎么玩", "analyze this repo"
- architecture, runtime, hook, MCP, capability, agent, skill, or tool routing
- commercialization, market, competitor, pricing, customer, investor, growth, strategy, roadmap, or current external-platform claims
- any durable execution request that will edit, test, publish, install, sync, release, or make a public-ready claim
Required Route
When one of the entry cases matches, Cursor must run or faithfully follow the machine entry:
npm run meta:theory:run -- "<user request>"
If the command cannot run because dependencies, permissions, shell access, or
runtime support are missing, stop before shallow analysis and record a blocker:
blocked_to_fetch with the exact missing capability. Do not answer from a
quick summary as if Fetch happened.
Deep Fetch Minimum
Project-understanding and strategy tasks must inspect or explicitly account for all of these source classes before Thinking:
README.md/README.zh-CN.mdAGENTS.mdand runtime-maintainer instructionspackage.jsonscripts and executable commandscanonical/agents/,canonical/skills/,canonical/runtime-assets/config/contracts/,config/capability-index/, runtime and OS matrices.cursor/,.claude/,.codex/, andopenclaw/runtime projections- MCP configs, heartbeat files, hooks, and dependency-project registry
- Graphify:
graphify-out/GRAPH_REPORT.mdorgraphify-out/wiki/index.mdwhen present - prior run/evolution records when the task asks about history or learning
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 · 77 lines · 776 tokens per session scan A c94eb53e30d8
meta-theory-dispatch is a cursor rule published in the GitHub repository KimYx0207/Meta_Kim (269 stars, last pushed yesterday), licensed Apache-2.0. It adds 776 tokens to every session, about $0.0039 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.