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 magnus919/agent-skills --skill electronicsgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/electronics)<a href="https://agentmods.dev/skills/magnus919/agent-skills/electronics"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/electronics/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/magnus919/agent-skills/electronics"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/electronics.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 | $0.00095 | $0.01758 |
| Opus 5.5 | $0.00038 | $0.00703 |
| Sonnet 5.5 | $0.00019 | $0.00352 |
| Haiku 4.5 | $0.00010 | $0.00176 |
Grade A, and why
electronics 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 1mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Electronics
Turn a desired physical behavior into a justified circuit and an observable verification result. Treat the schematic, components, layout, power source, load, measurement setup, and environment as one system. A plausible schematic or successful simulation is an intermediate artifact, not proof of a working assembly.
Working contract
- Identify the requested decision: explain, calculate, select, review, diagnose, build, or verify. Produce the artifact needed for that decision; do not demand a full design dossier for a bounded calculation.
- Record exact component and board identities when device-specific claims matter. Use the manufacturer datasheet revision, package and operating conditions. Separate recommended operation, absolute maximum, typical performance, guaranteed bounds and measured behavior.
- Model the relevant signal, power, timing and thermal paths. State units, sign conventions, assumptions and corners. Compute a useful conditional result from supplied hypothetical inputs; do not invent missing measurements or guaranteed ratings.
- Define acceptance before experimentation. Each measurement needs a predicted value/range, instrument configuration, validity limits and a decision it will resolve.
- Change one explanatory variable at a time when feasible. Preserve the initial symptom and distinguish observation from hypothesis and inference.
- Before changing wiring, applying power, driving signals or operating connected equipment, confirm the target, scope, and rollback path before acting. Read-only discovery may proceed without confirmation. Obtain the measurement and recovery plan appropriate to the actual energy and fault paths.
- Stop if the next action exceeds verified device, instrument or isolation limits. Missing high-risk facts require a bounded evidence request, not a guessed command or connection.
Route the work
Load only the references needed for the current decision. Each reference contains assumptions, worked reasoning, failure patterns and acceptance guidance; templates turn that reasoning into reviewable artifacts.
What ships with it
20 files 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.
- evals/evals.json 8.5 KB
- README.md 2.2 KB
- references/analog-and-digital-building-blocks.md 5.5 KB
- references/assembly-and-verification.md 3.6 KB
- references/component-selection.md 6.7 KB
- references/fault-isolation.md 3.0 KB
- references/i2c-integration.md 5.2 KB
- references/measurement-and-instrumentation.md 7.5 KB
- references/power-thermal-and-protection.md 6.5 KB
- references/schematic-to-bench.md 3.5 KB
- references/sensors-and-conditioning.md 5.8 KB
- references/tolerances-and-error-budgets.md 6.2 KB
- templates/assembly-acceptance.md 1.0 KB
- templates/bus-electrical-budget.md 850 B
- templates/component-contract.md 1.9 KB
- templates/design-calculation-record.md 1.2 KB
- templates/fault-ledger.md 672 B
- templates/measurement-plan.md 718 B
- templates/schematic-review.md 810 B
- templates/sensor-calibration-plan.md 1.4 KB
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.
- 1mo ago First seen · 89 lines · 95 tokens per session scan A 3be28cb66bf3
electronics is a skill published in the GitHub repository magnus919/agent-skills (133 stars, last pushed 2d ago), licensed MIT. It adds 95 tokens to every session and 1,758 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 2026-09-15.
Other skills, from other repositories
running-openmed-ondevice
Run OpenMed models fully on-device with the MLX (Apple Silicon), CoreML (iOS/macOS), or ONNX/WebGPU (cross-platform/browser) backends, including convert-quantize-run workflows. Use when the user wants to deploy OpenMed at the edge, run NER/de-id on Apple Silicon, target iPhone/iPad/Mac, export to ONNX or WebGPU…
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…
actual-setup
Set up Actual Computer (actual.inc) inference in Hermes.
eightctl
Control Eight Sleep pods (status, temperature, alarms, schedules).
klatch
Spawn genuinely independent parallel subagents — each assigned a distinct perspective role (Skeptic, Optimist, Pragmatist, Domain Expert, Contrarian) — to analyze a topic from independent viewpoints and synthesize divergent findings into a decision-ready roundtable output.
cocoplus-config
CocoPlus configuration SSOT — $cocoplus sync propagates cocoplus.toml into downstream artifacts; $cocoplus migrate-config converts legacy safety-config.json. Invoked via $cocoplus sync and $cocoplus migrate-config.