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 kh6570/HAbedini-qspice-mcp --skill qspice-convergence-debugginggit clone --depth 1 https://github.com/kh6570/HAbedini-qspice-mcpWrote 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/kh6570/habedini-qspice-mcp/qspice-convergence-debugging)<a href="https://agentmods.dev/skills/kh6570/habedini-qspice-mcp/qspice-convergence-debugging"><img src="https://agentmods.dev/badge/skills/kh6570/habedini-qspice-mcp/qspice-convergence-debugging/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/kh6570/habedini-qspice-mcp/qspice-convergence-debugging"><img src="https://agentmods.dev/badge/skills/kh6570/habedini-qspice-mcp/qspice-convergence-debugging.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 | $0.00073 | $0.01515 |
| Opus 5 | $0.00036 | $0.00758 |
| Sonnet 5 | $0.00015 | $0.00303 |
| Haiku 4.5 | $0.00007 | $0.00152 |
Grade A, and why
qspice-convergence-debugging 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 11d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QSpice: Convergence Debugging
A structured workflow for simulations that fail to converge, abort early, or yield empty/flat results. Convergence failures are about the numerics and the circuit, not the MCP server.
When to use
run_simulationreturns an error or the result has no/short waveform.read_logshows:no convergence,timestep too small,singular matrix,gmin stepping failed,iteration limit, or analysis stopped before the requested stop time.- A signal that should be active is flat or missing in
list_signals.
When NOT to use
connected=false/ missingQSPICE_EXE→ setup/config problem, not numerics.- Backend-unavailable errors → call
describe_server_capabilitiesfirst.
Workflow
- Read the evidence.
read_log— identify the exact failure phrase and the time/node where it stopped. Don't guess before reading the log. - Localize.
inspect_schematic+list_components— find the stage near the failing node (switching node, feedback, high-impedance net, nonlinear device). - Form one hypothesis from the table below and change one thing.
- Re-run
run_simulation, thenread_logagain. Iterate; change one factor at a time so you know what helped.
Common causes → fixes
| Log symptom | Likely cause | Fix |
|---|---|---|
singular matrix, floating node |
No DC path to ground; dangling net | Add a path to GND (large R to ground), fix unconnected pins; verify with list_components |
timestep too small |
Stiff switching, ideal edges, no parasitics | Add small series R / snubber; soften driver edges; .options cshunt=1e-12; relax reltol slightly |
no convergence at t=0 |
Hard DC operating point | Add .ic initial conditions; enable gmin/source stepping; add soft-start to sources |
| Stops mid-transient | Discontinuity / ideal switch chatter | Add hysteresis or RC snubber across the switch; add device parasitics; cap maxstep |
Nonlinear/behavioral (B) blowup |
Aggressive expression, divide-by-zero | Clamp/limit the B expression; add series resistance |
| Trap ringing (numerical oscillation) | Trapezoidal integration on stiff circuit | .options method=gear or .options feather=... (trap damping factor) |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 109 lines · 73 tokens per session scan A a5317dc09020
qspice-convergence-debugging is a skill published in the GitHub repository kh6570/HAbedini-qspice-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,515 once invoked, about $0.0004 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
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
competition-firmware-layout
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user asks to unpack firmware, map partition layout, inspect bootloader or init…
doca-flow
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware programming, read counters, match the Flow version to the installed DOCA release, and diagnose Flow API errors. Trigger on DOCA…
diagnose-driver-install
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
catc-troubleshoot
Catalyst Center troubleshooting workflows - device unreachable investigation, client connectivity issues, interface down analysis, site-wide outage triage, wireless roaming problems, integration with pyATS for CLI-level diagnostics. Use when a device is unreachable, a user reports connectivity problems, an interface…