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 fireostendere/mcp_diptrace --skill diptrace-bom-sourcinggit clone --depth 1 https://github.com/fireostendere/mcp_diptraceWrote 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/fireostendere/mcp_diptrace/diptrace-bom-sourcing)<a href="https://agentmods.dev/skills/fireostendere/mcp_diptrace/diptrace-bom-sourcing"><img src="https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/diptrace-bom-sourcing/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/fireostendere/mcp_diptrace/diptrace-bom-sourcing"><img src="https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/diptrace-bom-sourcing.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 | $0.00089 | $0.01015 |
| Opus 5.5 | $0.00036 | $0.00406 |
| Sonnet 5.5 | $0.00018 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
diptrace-bom-sourcing 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 8d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime access before selecting tools or declaring a capability unavailable. MCP tools and native/headless CLI are separate interfaces.
DipTrace BOM and sourcing
RAG: engineering memory by default — shared workflow. Bring component/nonideality, sourcing and design-course knowledge into BOM review, substitutions, margins and lifecycle tradeoffs; verify live stock and prices separately.
Prepare an auditable procurement BOM. Catalog searches and local documents are in scope; purchasing or changing the circuit requires authorization for those actions.
Baseline
- Resolve schematic/PCB revision, assembly variant, fitted/DNP state, board count, assembler, and allowed substitutions from the request and project.
- Discover live MCP tools, then use
get_document_info,run_review(profile="bom_basic"), andexport_bom. When both CAD documents exist, usecompare_schematic_to_pcb. Keep source hashes and original exports. - Normalize one row per exact manufacturer/MPN/package/variant combination, preserving RefDes membership. Record value, tolerance/rating, footprint, quantity per board, supplier code, stock/date, unit price/currency/price break, lead time, and evidence. Exclude Net Ports and documentary objects. Preserve DNP and hand-assembly lists.
- Multiply fitted quantity by board count; account explicitly for approved spares, attrition, MOQ, and order multiples. If the board count is unknown, complete the per-board BOM and leave order totals pending.
Source and compare
- Search exact installed parts with
query_builtin_library_catalogfirst. On a supported Windows host, this can export installed component libraries to an XML cache through hidden Component Editor without modifying the installed library. - For missing catalog data,
pipeline_source_componentresolves an MPN/LCSC code and writes combined EasyEDA JSON plus an available PDF into an explicit project vendor directory. It does not import a native library or reserve stock. Verify the exact MPN/package, JSON symbol and footprint records, and actual PDF content; preserve returned paths/hashes. Convert geometry only through a supported import or a validated project converter, checking units, orientation, pad geometry and pin-to-pad aliases. Check official package evidence with diptrace-datasheet-rules. - Verify stock, category, current orderability, price breaks, and assembly availability on the supplier/assembler's current service. Timestamp results. LCSC warehouse stock does not prove JLCPCB assembly stock; cached stock is not a reservation.
- For JLCPCB, prefer Basic, then Preferred Extended, then Extended among technically valid choices. Minimize unique types only when ratings, behavior, and packaging remain suitable. Use the chosen assembler's rules for other suppliers.
- Evaluate substitutes against function, pinout, package/land pattern, electrical limits, tolerances, temperature, dynamic behavior, and relevant firmware effects. Include capacitor effective capacitance, inductor saturation/current, and ferrite impedance/DC resistance when those characteristics matter to the circuit.
- A shared value or package name is not equivalence. Separate drop-in candidates from changes needing a new footprint, schematic, layout, firmware, or qualification. Propose an ECO through diptrace-revision-review when applicable; sourcing by itself does not apply substitutions.
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.
- 8d ago Changed 893069c12971
- 1mo ago First seen · 75 lines · 89 tokens per session scan A c73601be59e6
diptrace-bom-sourcing is a skill published in the GitHub repository fireostendere/mcp_diptrace (24 stars, last pushed 4d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,015 once invoked, about $0.0004 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 2026-09-13.
Other skills, from other repositories
fictiv
Operates Fictiv (app.fictiv.com), the on-demand manufacturing platform, end to end in the user's browser. Covers uploading CAD parts, configuring process, material, finish, threads, tolerances and inspections, getting instant or manual quotes, reading and fixing DFM feedback, choosing lead time and region, checking…
element14
Search Newark, Farnell, and element14 for electronic components — find parts by MPN or distributor part number, check pricing/stock, download datasheets, analyze specifications. One unified API covers all three storefronts (Newark for US, Farnell for UK/EU, element14 for APAC). Free API key, simple query-parameter…
coin-vending-amusement-machine-servicer
Use when a task needs the judgment of a Coin, Vending, and Amusement Machine Servicer and Repairer — triaging a jam across bill validators, coin mechanisms, refrigerated vending units, and arcade/amusement PCBs on a route, setting restock par levels against route-cycle economics, investigating a cash-collection…
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…