What is critical-net-router?

A controlled routing workflow for one named critical circuit connection or differential pair in DipTrace, a PCB design program. It uses bounded 45-degree pathfinding and checks the board before and after routing.

Use it to plan or route a critical PCB net or differential pair, inspect the proposed path, run design-rule checks, and commit only after confirmation.

It limits routing to an explicitly requested scope and adds checks for design rules, connectivity, file changes, and routing regressions.

critical-net-router — Skill for Claude Code and Codex by fireostendere

Install

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.

Any agent

npx skills add fireostendere/mcp_diptrace --skill critical-net-router

Clone the repo

git clone --depth 1 https://github.com/fireostendere/mcp_diptrace

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/critical-net-router/github.svg)](https://agentmods.dev/skills/fireostendere/mcp_diptrace/critical-net-router)

Your own site

<a href="https://agentmods.dev/skills/fireostendere/mcp_diptrace/critical-net-router"><img src="https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/critical-net-router/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fireostendere/mcp_diptrace/critical-net-router"><img src="https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/critical-net-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 944 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00085	$0.00944
Opus 5.5	$0.00034	$0.00378
Sonnet 5.5	$0.00017	$0.00189
Haiku 4.5	$0.00009	$0.00094

Measured 28d ago against content hash 8166d077a21c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

critical-net-router 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.

skills/critical-net-router/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 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.

Critical-net router

RAG: engineering memory by default — shared workflow. Consult routing/return-path and transmission-line material before choosing constraints; use DipTrace PCB courses for implementation and verify the actual route.

Route an explicitly named scope. The local router is deterministic bounded 45-degree A*, not push-and-shove. Use public tools/list for exact callable names and get_capabilities for document/configured feature availability.

Workflow

Call diptrace_status, get_capabilities, and get_document_info; require a PCB and freeze the SHA-256.
Read get_design_rules, list_unrouted_connections, and analyze_routing_congestion. Require concrete endpoints, allowed layers, via policy, and net or pair identity.
For one connection use route_connection; for exported ratlines use route_net. For a real pair use plan_diff_pair_route or route_diff_pair; never route the two legs independently.
Omit clearance only to resolve the document DRC TraceToTrace rule. An explicit caller value is millimetres and must be named in the report.
Prefer plan_route_nets plus apply_route_plan for a reviewable plan. Inspect SVG/JSON, then validate and use an expected_sha256 commit within the already authorized routing scope. A request for a plan alone never authorizes committing it.
Run run_review(profile="drc_basic") and run_review(profile="connectivity"); rollback only this session's failed changes with a current hash guard. When native validation is in scope, use the headless PCB acceptance workflow; offline DRC does not invoke the real editor.
Emit ../shared/result.schema.json.

Quantitative boundaries

One local route plan accepts at most 20 connections.
route_connection defaults to zero vias, a 3.0 detour factor, and at most 100,000 search nodes.
Multi-route rip-up/retry defaults to four attempts; this remains bounded local retry, not push-and-shove.
A transaction accepts at most 100 operations and 500 conservatively counted affected objects/elements; this can be fewer than 500 unique physical objects.

Read the full file on GitHub · 63 lines

Changes

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 · +39 tokens per session 8166d077a21c
1mo ago Changed · +10 lines · +4 tokens per session 24b83567c340
2mo ago First seen · 53 lines · 42 tokens per session scan A c0fe4b2b81ae

Subscribe to this mod's changes

critical-net-router is a skill published in the GitHub repository fireostendere/mcp_diptrace (25 stars, last pushed 24d ago), licensed Apache-2.0. It adds 85 tokens to every session and 944 once invoked, about $0.0003 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.

Hardware and IoT

critical-net-router next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
critical-net-routerfireostendere/mcp_diptrace	Skill	25	24d ago	Apache-2.0	A	85	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