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 flintt-dev/boardrepo-plugin --skill boardrepogit clone --depth 1 https://github.com/flintt-dev/boardrepo-pluginWrote 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/flintt-dev/boardrepo-plugin/boardrepo)<a href="https://agentmods.dev/skills/flintt-dev/boardrepo-plugin/boardrepo"><img src="https://agentmods.dev/badge/skills/flintt-dev/boardrepo-plugin/boardrepo/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/flintt-dev/boardrepo-plugin/boardrepo"><img src="https://agentmods.dev/badge/skills/flintt-dev/boardrepo-plugin/boardrepo.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 | $0.00156 | $0.01576 |
| Opus 5 | $0.00078 | $0.00788 |
| Sonnet 5 | $0.00031 | $0.00315 |
| Haiku 4.5 | $0.00016 | $0.00158 |
Grade A, and why
boardrepo 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 9d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BoardRepo
BoardRepo is a library of real, published PCB projects, plus a private home for the user's own boards. This skill is about using the BoardRepo MCP tools well — which one answers which question, and in what order. It is not a description of the tools; each tool carries its own description, and those are authoritative on arguments.
The one rule that is not here
The server sends a DESIGN REVIEW CONTRACT in its initialize instructions whenever the
review tools are available. It is the authority on how to report a review, and it is
deliberately not summarised here — not even as a list of what it covers, because a summary
is a second copy and the copy a reader happens to find is the one that wins.
Follow the contract the server sent you. This file only tells you which calls to make.
Getting to a board
Every board-reading tool takes a board reference, and you need one before anything else.
| You have | Do this |
|---|---|
a boardrepo.com URL, or handle/slug |
pass it straight to get_board |
| a part number, or a vague description | search_boards, then get_board on the row you want |
| "my boards" | list_my_boards — needs own-board access |
search_boards searches published boards. If the user means a board of their own and
it is not public, search_boards will not find it: use list_my_boards.
If a board reference comes back not-found, take that at face value. A board that exists but is not visible to this connection is reported identically to one that does not exist — there is no way to tell them apart, and guessing is worse than saying you could not find it.
Reading a design
Ask the question you actually have, rather than reading files and inferring.
- "What is it made of?" →
get_bom. Reference designators, values, footprints, MPNs. - "What connects to U3?" / "what is on GND?" →
read_schematicwithrefornet. This is the tool that separates you from guessing: without it you are recalling what a part's datasheet says, not reading what this designer drew. - "What files are in it?" →
list_board_files, thenread_filefor one of them. - "Find X inside the design" →
search_board, orquery_designfor structure.
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.
- 9d ago First seen · 122 lines · 156 tokens per session scan A 293b57169b77
boardrepo is a skill published in the GitHub repository flintt-dev/boardrepo-plugin (0 stars, last pushed 15d ago), licensed MIT. It adds 156 tokens to every session and 1,576 once invoked, about $0.0008 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 skills, from other repositories
loop2converge
The closed convergence loop for ANY benchmark subject — open-benchmark Evaluation, benchmark IC (doc→GDS), or IP-cell (doc→LEF/GDS). RUN the canonical front door, CLASSIFY every FAIL as flow / gate / tool, CONVERGE it by fixing the layer that owns it, PROVE the fix in the plugin cache against the real artefacts BEFORE…
phase1-coverage-loop
Closed-loop field-agent for Phase 1 coverage. Rotates through a benchmark IC folder (e.g. 2ndbanchmark/) running /vibe-ic-phase1 on each IC's README/prompt, measures input→L1-L27 token completeness with phase1inputvsgeneratedcompletenesscheck, and files chip-AGNOSTIC plugin backlog issues for systematic ingester gaps.…
formal-verify
Run formal property verification (FPV) on RTL by driving model-checkers such as SymbiYosys, Jasper, or VC Formal. Use when the user says "prove this", "formal verify", "model check", "run sby", or has SVA properties from assertion-gen that need to be proven or bounded.
phase2-rtl-verify
After designoneshotrunner emits RTL + SOF + reference TB PASS, AI spot-checks RTL quality and L9-contract conformance. Triggers when /vibe-ic-phase2 / /vibe-ic-phase2 returns PASS, or on phrases like "review the RTL", "check RTL quality", "verify phase 2 output".
analog-output-verify
After analogoneshotrunner emits A1..A9 outputs, AI spot-checks corner-sim coverage, hardmacro completeness, HIL data fidelity. Triggers on /vibe-ic-analog PASS or phrases like "review analog", "verify A8 hardmacro", "check analog corners".
scope-pattern-attestation
Layer-3 hardware attestation — talk to an oscilloscope via SCPI to verify behavioral patterns (or absence of patterns) on real silicon IO. Use when sim and static RTL checkers can both pass but you need to confirm the actual hardware doesn't exhibit a forbidden timing pattern (e.g. periodic wake pulses that should…