Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add JMMonte/agentic-digital-twin/plugin install agentic-digital-twinWrote 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/jmmonte/agentic-digital-twin/run-tradeoff-study)<a href="https://agentmods.dev/skills/jmmonte/agentic-digital-twin/run-tradeoff-study"><img src="https://agentmods.dev/badge/skills/jmmonte/agentic-digital-twin/run-tradeoff-study/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/jmmonte/agentic-digital-twin/run-tradeoff-study"><img src="https://agentmods.dev/badge/skills/jmmonte/agentic-digital-twin/run-tradeoff-study.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 | $0.00099 | $0.00949 |
| Opus 5 | $0.00049 | $0.00475 |
| Sonnet 5 | $0.00020 | $0.00190 |
| Haiku 4.5 | $0.00010 | $0.00095 |
Grade A, and why
run-tradeoff-study 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 9d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a scored tradeoff study
Gut picks lose. A scored study with sensitivity earns its keep — it has overturned the "obvious" choice repeatedly. This skill runs one correctly.
The method (four rules)
- Cheapest fidelity that discriminates. Evaluate candidates at the PLACEMENT level — box layouts over the exported sections/rings — NOT a full build per candidate. Build only the winner.
- Score on COMPUTED physics. CG, inertia, margin, density, containment, clearance — computed from the candidate parameters, not asserted.
- Sensitivity, then ROBUST winner. Sweep several weight schemes (equal / performance-leaning / serviceability-leaning / ...). Pick the candidate that wins the MOST schemes, not the one that wins a single weighting. A lone-weighting winner hides ties and fragile leads.
- Side by side. One rerun
Spatial3DViewPER candidate, tiled in a grid (arrb.Gridof views). Never overwrite one recording per candidate — the whole point is to see them together.
The gotchas (each cost a wrong answer once — see GUARDRAILS.md §4)
np.interprequires ASCENDINGxp. For "lower is better" use ascendingxpwith REVERSEDfp(np.interp(x, [lo, hi], [5, 2])). A descendingxpdoes not raise — it SILENTLY INVERTS the metric and makes the worst candidate look best.- Score what actually constrains, not a proxy that looks placed. E.g. pack DENSITY (kg/L) catches a box too small to hold its cells; a "placed" box can still be infeasible.
- Containment vs the REAL ring, not an assumed beam. A V-bottom + tumblehome hull means a side box pokes out the TOP corner as well as the bottom. Check against the exported section, not an envelope you imagined.
- Drop metrics that don't discriminate. If a metric is ~constant across candidates (e.g. CG_x when payload sits at the CG), it earns no column — find one that separates them.
Procedure
- If the project already has
tradeoff.py(fromscaffold-hw-project), start there. Otherwise copy the template:cp "${CLAUDE_PLUGIN_ROOT}/skills/scaffold-hw-project/templates/tradeoff.py" ./tradeoff.py
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.
- 9d ago First seen · 76 lines · 99 tokens per session scan A dd86163ceec9
run-tradeoff-study is a skill published in the GitHub repository JMMonte/agentic-digital-twin (2 stars, last pushed 2mo ago), licensed MIT. It adds 99 tokens to every session and 949 once invoked, about $0.0005 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
cad-construction
Use after the design concept is settled (via design-first-iteration or equivalent) and the user is ready to translate it into parametric CAD geometry — component decomposition, parameter hierarchy, construction sequencing. Primary platform Fusion 360; the workflow also applies to SolidWorks, Onshape, FreeCAD…
bom-validation-workflow
Use when validating a Bill of Materials (BOM) for a Maker-3D project — an embedded controller project, a speaker/audio build, a smart-home build, or any other physical build with more than 5 components. Trigger on phrases like "check the BOM", "validate the parts list", "review the parts list", "missing components"…
victron-cerbo-modbus-device-onboarding
Use when a new Victron Modbus-TCP device (EV Charging Station, energy meter, inverter) is connected to the Cerbo GX LAN but does not appear in the Cerbo UI or D-Bus, despite being reachable via ping. Trigger on phrases like "EVCS not visible in Cerbo", "new Modbus device does not appear", "Cerbo does not detect…
mechanical-design-principles
Guides mechanical design decisions toward elegant, manufacturable, serviceable solutions with a strong bias toward tool-less assembly, monolithic parts, and form-follows-function. Provides the design rules (the WHAT and WHY — overhang, wall thickness, snap-fit sizing, tolerances, material matching). Load when the user…
hsb-ip-packetizer
Choose or explain HSB Sensor RX packetizer fields for HOLOLINKdef.svh. Do not use for full defs, validation, or runtime APB programming.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.