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 signal-integrity-reviewgit 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/signal-integrity-review)<a href="https://agentmods.dev/skills/fireostendere/mcp_diptrace/signal-integrity-review"><img src="https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/signal-integrity-review/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/signal-integrity-review"><img src="https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/signal-integrity-review.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 | $0.00093 | $0.01067 |
| Opus 5.5 | $0.00037 | $0.00427 |
| Sonnet 5.5 | $0.00019 | $0.00213 |
| Haiku 4.5 | $0.00009 | $0.00107 |
Grade A, and why
signal-integrity-review 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 28d 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 choosing between explicit-path MCP, a live bridge session, and native/headless CLI. Their availability is separate.
Signal-integrity review
RAG: engineering memory by default — shared workflow. Use the indexed transmission-line, grounding and EMC material to justify the model, assumptions and return-path checklist; solver output does not replace that basis.
Keep analytical equations, geometry heuristics, and external solver output in separate evidence
classes. No result is fabrication sign-off.
Use public tools/list for exact callable names and get_capabilities for document/configured
feature and adapter availability.
Scope selection
microstrip: supported single-ended analytical model for an outer-layer trace.differential_microstrip: supported coupled analytical model with explicit gap.symmetric_stripline: supported single-ended analytical estimate within its published range.- Differential stripline: unavailable; return
blocked_by_capability. run_openems_stripline_analysis: a registered typed external adapter, not a bundled solver.run_ngspice_simulation: a registered batch adapter for a caller-supplied netlist, not a PCB geometry extractor.
Workflow
- Call
diptrace_status,get_capabilities, andget_document_info; freeze the PCB SHA-256. - Read
get_stackupandget_route_details. Require explicit net, layer, dielectric height/permittivity, copper width/thickness, reference conductor, and target/tolerance when a pass/fail judgment is requested. - Use
calculate_impedancefor standalone inputs,analyze_stackup_for_impedancefor complete outer-layer microstrip stackups, andvalidate_impedance_constraintsfor named routed nets. - Use
analyze_return_pathonly as a caller-radius geometry heuristic. Disclose boundary-only pour geometry, layer-transition ambiguity, and confidence limits. If native refill evidence is needed, use the PCB headless profile on a copy and retain its exported geometry and verdict; do not call all native work unavailable based on the MCP tool list. Even refilled geometry does not turn this heuristic into a field solution. - Invoke ngspice/openEMS only when runtime discovery says the configured adapter is available. For openEMS retain request SHA-256, solver version, convergence, result SHA-256, and resources. For ngspice retain the netlist SHA-256, job status, return code/log summary, and resources; its current API exposes no executable version, convergence field, or result SHA-256, so record those fields as unavailable instead of inventing them.
- Emit
../shared/result.schema.json. Put impedance, effective permittivity, length/skew, frequency, and return-path coverage values inmeasurements, each with a unit, evidence class, and evidence IDs; do not hide numeric evidence in prose.
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.
- 28d ago Changed · +41 tokens per session 9b126cf8e893
- 1mo ago Changed · +10 lines · +4 tokens per session eb6f4c49e03d
- 2mo ago First seen · 65 lines · 48 tokens per session scan A ef6bd0d430d8
signal-integrity-review is a skill published in the GitHub repository fireostendere/mcp_diptrace (25 stars, last pushed 24d ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,067 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 2026-08-30.
signal-integrity-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| signal-integrity-reviewfireostendere/mcp_diptrace | Skill | 25 | 24d ago | Apache-2.0 | A | 93 | Claude Code, Codex |
| gke-compute-classesgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| jetson-diagnosticNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code, Codex |
| holoscan-install-wheelNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 34 | Claude Code, Codex |
| offensive-z-waveSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 113 | Claude Code, Codex |
| doca-socket-relayNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 236 | Claude Code, Codex |
| hsb-flashNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | B | 94 | Claude Code |