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.
npx skills add OutlineDriven/outline-driven-development --skill bootloaders-embeddedgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/skills/outlinedriven/outline-driven-development/bootloaders-embedded)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/bootloaders-embedded"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/bootloaders-embedded/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/skills/outlinedriven/outline-driven-development/bootloaders-embedded"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/bootloaders-embedded.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.01579 |
| Opus 5 | $0.00023 | $0.00790 |
| Sonnet 5 | $0.00009 | $0.00316 |
| Haiku 4.5 | $0.00005 | $0.00158 |
Grade A, and why
bootloaders-embedded 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 3d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Embedded bootloaders
Contract
| Field | Bound contract |
|---|---|
| Trigger | An application must run at a non-zero flash offset, a bootloader must validate and jump to it, a firmware update path (UART, USB DFU, custom protocol) is being written, or an application works when flashed alone but fails when launched by the bootloader. |
| Authority | Read-only: emits the flash layout, validation checks, handoff sequence, and update-safety rules to chat; the user places them in the project. Rollback is not needed because no file is written. No remote mutation. |
| Side effect | Chat output only. |
| Done | The flash partition table, the application validity check, the ordered handoff sequence, and the update commit rule are stated for the target part, and the application-side VTOR and linker changes are named. |
Inputs
- Target part and its flash map: base address, sector or page sizes, and whether it has two banks.
- Bootloader size budget and the chosen application base address.
- Update transport (UART, USB DFU, external flash, none).
- Where the update request flag lives (RTC backup register, GPIO strap, magic word in RAM).
- Whether the vendor part has a system-memory bootloader and which transports it lists in the vendor application note (AN2606 for STM32).
Procedure
-
Fix the flash layout and relink both images to it. The bootloader starts at the flash base; the application starts at a sector boundary above it and its vector table sits at that base. Done when: the application linker script sets
FLASH ORIGINto the application base and the bootloader never writes below it.Region Address (STM32 example) Content Bootloader 0x08000000Boot code and update logic, typically 16 KB to 64 KB Application 0x08010000Application vector table then code -
Validate the application image before jumping. Vector 0 must point into RAM; vector 1 must point into the application's flash range and carry the Thumb bit (bit 0 set). Add a CRC or magic word in an application metadata section when the update path can leave a half-written image. Done when: the check rejects an erased sector (
0xFFFFFFFFin both vectors) and accepts a good image.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 95 lines · 47 tokens per session scan A f471c81ed016
bootloaders-embedded is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,579 once invoked, about $0.0002 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 2026-09-06.
Other skills, from other repositories
automatic-cybernetic-flow-design
Use when the user wants a cybernetic flow design document for an interactive system. Specifies sensors, actuators, feedback paths, delays, and oscillation risk, and writes the design to a named local file. Not for implementing or deploying the system.
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
unifi-protect
How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, Known Faces, license plates, and the Alarm Manager. Use this skill when the user mentions UniFi cameras, security cameras, NVR, recordings, motion detection, person…
mi300-hip-vs-nvidia
MI300 HIP programming differences vs NVIDIA—wavefront vs warp, memory hierarchy, MFMA usage, occupancy, and profiling pitfalls.
gpu-memory-model
GPU memory model skill for SIMT execution and memory hierarchy. Use when analyzing warp divergence, memory coalescing, shared memory bank conflicts, cache behavior, atomics, or occupancy tradeoffs. Activates on queries about SIMT, warp coalescing, bank conflicts, wavefront, GPU occupancy, or memory-bound kernels.
ios-build-cleanup
Use when the user wants a clean Xcode rebuild by deleting DerivedData and build artifacts. Do not use for diagnosing a specific build error: use ios-build-fix.