agentmods.dev

guardrails-check

guardrails-check is a skill for Claude Code from JMMonte/agentic-digital-twin. It costs 91 tokens per session (919 once invoked), scanned A, original, MIT.

A checklist for checking whether results from hardware design and simulation work are actually correct. It focuses on failures that produce plausible numbers without raising an error, such as incorrect geometry or interpolation.

In plain words
What is it for?
Use it before trusting or reporting results from voxel or CAD geometry, fluid simulations, audits, or value-to-score calculations.
Why use it?
A process completing without errors does not prove its output is right. The checklist requires each important result to be compared with an independent reference, formula, or exported file.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agentic-digital-twin plugin — 8 skills, 1 agent shipped together

not rated 2repo 2mo ago A scan 91 tokens original MIT

Good fit Use it before trusting or reporting results from voxel or CAD geometry, fluid simulations, audits, or value-to-score calculations.

Compare 6 skills from other repositories ↓
View source ↗ JMMonte/agentic-digital-twin
Install

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.

Claude Code
/plugin marketplace add JMMonte/agentic-digital-twin
Claude Code
/plugin install agentic-digital-twin

Made for: Claude Code.

Or install agentic-digital-twin, the plugin that ships this one along with the rest of its 8 skills, 1 agent.

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.

agentmods badge for guardrails-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/jmmonte/agentic-digital-twin/guardrails-check/github.svg)](https://agentmods.dev/skills/jmmonte/agentic-digital-twin/guardrails-check)
Your own site
<a href="https://agentmods.dev/skills/jmmonte/agentic-digital-twin/guardrails-check"><img src="https://agentmods.dev/badge/skills/jmmonte/agentic-digital-twin/guardrails-check/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.

agentmods 80×15 button for guardrails-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/jmmonte/agentic-digital-twin/guardrails-check"><img src="https://agentmods.dev/badge/skills/jmmonte/agentic-digital-twin/guardrails-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 919 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.00919
Opus 5 $0.00046 $0.00460
Sonnet 5 $0.00018 $0.00184
Haiku 4.5 $0.00009 $0.00092

Measured 10d ago against content hash d70012b30528, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

guardrails-check 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 10d 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/guardrails-check/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guardrails check (and how to grow the checklist)

The meta-rule: a result that "ran clean" is not a result that is correct. Voxel kernels, CFD configs, and np.interp fail SILENTLY — no exception to catch — which is the worst failure mode for an agent. Every derived number must agree with an independent anchor before you trust it.

The full, living checklist is ${CLAUDE_PLUGIN_ROOT}/GUARDRAILS.md (and the project-local copy at <project>/GUARDRAILS.md after scaffolding). Read it. This skill is the workflow for using it and keeping it current.

Before declaring ANY result correct, sweep these

  • Wrong boolean, clean mesh. A failed subtract / flood-filled cavity / no-op union still yields a watertight, positive-volume mesh. Did an audit assert the EXPECTED bbox/volume/CG, not just ">0"?
  • np.interp direction. Any value→score map: is xp ascending? Is lower-is-better done with ascending xp + REVERSED fp? Hand-check a value at each end of the band.
  • Anchor cross-check. Is every derived number checked against a [PUB] value, an analytic formula, or the REAL exported artifact — not an assumed envelope?
  • Voxel/CAD silence. Union first, subtract last, vent every cavity? No voxel artifact on the outer mold line (sub-voxel wall reads as closed)? Loft ruled= pinned?
  • CFD config. FLUID_MODEL set explicitly (ideal-gas trap)? Validated against an analytic anchor and a grid-convergence study?
  • Sim signs + indices. Every control-derivative sign written down and self-checked at runtime? State-vector slices named (the v-vs-w trap)? Subsystems calibrated open-loop before closing the loop?
  • rerun. rr.save() before opening the viewer (it REPLACES the sink)? vertex_normals on every Mesh3D? Milestone archived to out/history/<date>/ before regenerating?
  • Mesh hygiene. Decimated before queries? Degenerate faces cleaned (update_faces(nondegenerate_faces()), np.nanmax)?
  • Look at it. Did you open the render — including the underside and the region you touched?

Read the full file on GitHub · 72 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.

  1. 10d ago First seen · 72 lines · 91 tokens per session scan A d70012b30528

Subscribe to this mod's changes

guardrails-check is a skill published in the GitHub repository JMMonte/agentic-digital-twin (2 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 919 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.

Claude CodeHardware and IoTTestingagentic-aiai-agentscadclaude-code-plugindigital-twin
Related

Other skills, from other repositories

jetson-video-pipeline

Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or acceptance workflows with exact artifact handoffs.

NVIDIA/skills · 45 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

holohub-app-lifecycle

Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.

NVIDIA/skills · 40 tokens

tia-testsuite

TIA Portal V21 Test Suite operations. Use for Application Tests with PLCSIM, Style Guide rules, System Tests through OPC UA, import/scope management, execution, and recursive result evaluation.

Czarnak/totally-integrated-claude · 43 tokens

simulation

Use when materializing and running a module's UVM TB from an approved verification plan (regression, coverage); not for plan authoring or RTL changes.

chipweaver/veripower · 34 tokens

archetype-lint

This skill should be used when the user asks to "lint an archetype", "validate an archetype", "check archetype compliance", "check archetype rules compliance", or "run archetype rules". Applies 24 normative lint rules with ERROR/WARNING/INFO severity. Supports STRICT and PERMISSIVE modes. Reports violations only — it…

Cadasto/openehr-assistant-plugin · 130 tokens