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 JMMonte/agentic-digital-twin --skill add-scored-auditgit clone --depth 1 https://github.com/JMMonte/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/add-scored-audit)<a href="https://agentmods.dev/skills/jmmonte/agentic-digital-twin/add-scored-audit"><img src="https://agentmods.dev/badge/skills/jmmonte/agentic-digital-twin/add-scored-audit/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/add-scored-audit"><img src="https://agentmods.dev/badge/skills/jmmonte/agentic-digital-twin/add-scored-audit.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 | $0.00088 | $0.00893 |
| Opus 5 | $0.00044 | $0.00447 |
| Sonnet 5 | $0.00018 | $0.00179 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
add-scored-audit 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 12d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a scored audit check
A requirement that is not in an audit is a requirement that will silently regress. This skill adds one check the right way.
The rules a check must follow
- Read, don't redeclare. Pull the value from
design/design.jsonor a build-exportedout/*.jsonartifact. NEVER hard-code a geometry constant in the audit (regex it from the build source or read the JSON). A duplicated constant drifts and the audit then verifies a fiction. - Assert an EXPECTED value, not existence. The gold guardrail: a wrong
boolean still passes
watertight+volume>0. So check that the as-built bbox / volume / CG / margin matches a known anchor within a tolerance — not merely that it is positive. - Three outcomes. PASS, WARN (an HONEST, documented shortfall — e.g. physics contradicting a marketing claim), or FAIL (a real violation that must gate). Never use WARN to bury a real FAIL.
- Cross-check against an anchor. A derived number is only trustworthy
when it agrees with an independent truth: a published
[PUB]value, an analytic formula, or the REAL exported artifact.
Procedure
-
Open the project's
audit.py. Identify (or add) the right section header (sec = "N section name"). -
Find the source of truth for the value being checked:
- a
[PUB]anchor or requirement indesign/design.json, or - a build-exported artifact in
out/(bbox, volume, contact, section). If the build does not yet export what you need, add the export to the build FIRST (that is the source-of-truth discipline), then read it here.
- a
-
Add the check. For a value-vs-anchor check, prefer the
expect()helper:sec = "2 clearances" prop_clearance = COMP["prop"]["bboxMin"][2] - deck_top_z # from out/*.json req = D["requirements"]["prop_clearance_min_mm"]["min"] check(sec, "prop clears deck", prop_clearance >= req, f"clearance {prop_clearance:.1f} mm >= req {req} mm")For an as-built-matches-design check (the gold rule), assert the expected value, not just presence:
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.
- 12d ago First seen · 80 lines · 88 tokens per session scan A 515b100de229
add-scored-audit is a skill published in the GitHub repository JMMonte/agentic-digital-twin (2 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 893 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
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.
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.
holohub-app-lifecycle
Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.
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.
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.
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…