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/kot149/zmk-layout-shiftWrote 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/kot149/zmk-layout-shift/zmk)<a href="https://agentmods.dev/rules/kot149/zmk-layout-shift/zmk"><img src="https://agentmods.dev/badge/rules/kot149/zmk-layout-shift/zmk/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/kot149/zmk-layout-shift/zmk"><img src="https://agentmods.dev/badge/rules/kot149/zmk-layout-shift/zmk.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00557 | $0.00557 |
| Opus 5.5 | $0.00223 | $0.00223 |
| Sonnet 5.5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
zmk 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ZMK Project Coding Instructions for AI
Project Overview
For detailed project overview, features, and usage instructions, please refer to README.md.
Critical Prerequisites
MANDATORY: Before making ANY implementation changes, you MUST:
-
Consult the ZMK Repository Expert: Query the Deepwiki MCP server (repoName:
zmkfirmware/zmk) to understand the current implementation and identify potential issues. -
Consult the Zephyr Repository Expert: Since ZMK is Zephyr-based, also query the Deepwiki MCP server (repoName:
zephyrproject-rtos/zephyr) for Zephyr-specific implementation details when needed. -
Share Context: Provide the MCP server with:
- Current implementation details
- Identified problems or requirements
- Your proposed implementation approach
-
Validate Implementation Strategy: Confirm your implementation plan with the ZMK expert before proceeding.
-
Update Documentation: After making any changes, always update the README.md with relevant information about new features, usage instructions, or implementation status.
Why This Process is Essential
- Pre-trained Knowledge Limitations: LLM training data may not reflect the latest ZMK architecture, APIs, or best practices
- Build Failure Prevention: ZMK has specific conventions and dependencies that may not be obvious from general knowledge
- Implementation Accuracy: The ZMK codebase has evolved significantly, and outdated approaches will likely fail
Remember
NO ASSUMPTIONS: Always verify current ZMK practices before implementation. What worked in older versions may not work in current releases.
EXPERT FIRST: Consult zmkfirmware/zmk and zephyrproject-rtos/zephyr repository experts before coding, not after encountering build failures.
Build Verification
MANDATORY BUILD CHECK: After any implementation or modification, verify that the build passes by running the following command:
just build roBa_R -S zmk-usb-logging
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.
- 1mo ago First seen · 60 lines · 557 tokens per session scan A 4f5b28c2009d
zmk is a cursor rule published in the GitHub repository kot149/zmk-layout-shift (17 stars, last pushed 27d ago), licensed MIT. It adds 557 tokens to every session, about $0.0022 per session on Opus 5.5. 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 2026-09-01.
Other cursor rules, from other repositories
audio-streaming
Configure and receive PCM audio with Camera Stream on iOS.
20-angular-services
Angular service rules for wrapping web-serial-rxjs.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.