nightrun skillA
nightrun is agent-read markdown (skill) from akillness/jeo-skills: Build, test, run, and flash NightRun — a bare-metal, no_std Rust UEFI application that boots straight into a local LLM (Llama 3.2, Qwen3, or Granite 4.1) with no operating system underneath. Use when the user wants to build/flash a bootable NightRun USB or Raspberry Pi 5 SD image, convert a GGUF model into the `.nrm` container, run/debug the inference engine on the host or in QEMU/OVMF, or troubleshoot no_std kernel/tokenizer parity issues in the NightRun codebase. Triggers on: "nightrun", "boot.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# NightRun NightRun is a single `no_std` Rust UEFI application that boots directly into a chat prompt for a quantized local LLM (Llama 3.2, Qwen3, or dense Granite 4.1) — no Linux, no kernel, no browser, no network stack. The model is streamed into RAM with inline CRC-32 verification, storage is sealed once loaded, and inference runs entirely on-CPU (AVX2+FMA+F16C on x86_64, NEON on Pi 5). This skill drives the build → convert → test → flash workflow safely. ## When to use this skill - Building `BOOTX64.EFI` or a full bootable `nightrun.img` from source - Converting a GGUF checkpoint into the `.nrm` container with `nrconvert` - Running/debugging the inference engine on the host (`nrhost`) before reaching for QEMU - Booting NightRun in QEMU/OVMF (`cargo xtask run`) for screenshots or scripted verification - Flashing a real USB stick or Raspberry Pi 5 SD card via `install.sh` - Diagnosing tokenizer/parity failures against llama.cpp reference fixtures ## When not to use this skill - General local-LLM serving without bare-metal/no-OS constraints → use a normal inference runtime, not this skill - Generic Rust workspace refactors unrelated to the boot/model/kernel path → …
Read the whole file at its exact version.
How to install
mdr add akillness/jeo-skills/nightrun@v1.0mdr add akillness/jeo-skills/nightrun@sha256:9e27f9c87c5ff442Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_ki7sf3q2t72zebew)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7238 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
akillness/jeo-skills · 47 stars · license none · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ki7sf3q2t72zebew GET https://markdownregistry.com/api/v1/resolve?ref=akillness/jeo-skills/nightrun GET https://markdownregistry.com/api/v1/blob/9e27f9c87c5ff442f5f580480e8f3d3088a8e0c1ac3959743970cb3b00f90d71
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.