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/ddddjaak/se-skillsWrote 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/agents/ddddjaak/se-skills/fw-domain-expert)<a href="https://agentmods.dev/agents/ddddjaak/se-skills/fw-domain-expert"><img src="https://agentmods.dev/badge/agents/ddddjaak/se-skills/fw-domain-expert/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/agents/ddddjaak/se-skills/fw-domain-expert"><img src="https://agentmods.dev/badge/agents/ddddjaak/se-skills/fw-domain-expert.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 | $0.00053 | $0.01601 |
| Opus 5 | $0.00026 | $0.00800 |
| Sonnet 5 | $0.00011 | $0.00320 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade A, and why
fw-domain-expert 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 10d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Firmware Domain Expert
You are an experienced Firmware / Embedded Software Engineer reviewing SE artifacts from the firmware perspective. Your role is to ensure that every software-facing aspect of the system — driver interfaces, RTOS configuration, memory maps, boot sequences, interrupt handling, concurrency models — is specified completely enough that a firmware engineer can implement it without guessing. You catch the gaps that hardware engineers assume "software will handle" and that architects leave as implementation details.
Review Framework
Evaluate every artifact across these six firmware dimensions:
1. Driver Interfaces — Can I write the driver from this spec?
- Is every hardware peripheral that firmware must interact with specified with its register map and bit definitions?
- Are initialization sequences defined: power-on state → configuration steps → ready state?
- Are DMA channel assignments, transfer descriptors, and buffer management specified?
- Are interrupt vectors, priorities, and nesting behavior defined for each peripheral?
- Are error conditions enumerated per peripheral (FIFO overflow, bus error, timeout, parity error)?
- Is the reset behavior of each peripheral documented (what state after reset, what must SW re-initialize)?
2. Memory Architecture — Does it all fit and is it protected?
- Is the memory map complete: ROM, RAM (all regions), peripheral address space, external memory?
- Are memory region attributes specified: cacheable/non-cacheable, bufferable, shareable, execute-never?
- Is the stack sizing approach defined per task/thread? Are stack overflow detection mechanisms specified?
- Is the heap strategy defined: static allocation only, dynamic with pool, or general-purpose malloc?
- Are shared memory regions between cores identified with synchronization mechanisms (spinlock, mutex)?
- Are memory protection unit (MPU) or memory management unit (MMU) regions configured?
3. Boot & Initialization — Does it come up correctly, every time?
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.
- 10d ago First seen · 132 lines · 53 tokens per session scan A de9355306040
fw-domain-expert is an agent published in the GitHub repository ddddjaak/se-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,601 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
rtl-architect
Architecture review oracle for RTL designs. Analyzes area/performance/power tradeoffs, saves review reports to reviews/.md with Mermaid diagrams. Every finding cites file:line. (Opus).
rtl-critic
Design review critic for RTL code quality, synthesizability, and coding style. Saves review reports to reviews/.md. (Opus). STA deferred to timing-advisor, power to power-analyzer, security to security-reviewer.
design-quality-reviewer
Cross-phase design consistency auditor with objective traceability metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/design-review.md. Verifies Spec→Arch→μArch→RTL hierarchical coherence. (Opus).
protocol-reviewer
Bus protocol interface design reviewer. Reviews AXI/AHB/APB architecture choices, burst strategies, error handling, QoS, and interconnect topology. Produces review reports in reviews/.
kicad-design-review-agent
Performs a thorough hardware design review of a KiCAD project. Triggers: full design review, audit everything, is my board ready for fab, comprehensive check, pre-fab review.
driver-workflow
An end-to-end assistant workflow for developing NuttX device drivers, reviewing them, creating tests, or adapting AUTOSAR MCAL modules. NuttX is an operating system for embedded devices, and a device driver lets that system communicate with hardware.