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 5.5 | $0.00035 | $0.00357 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo 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 4mo ago), licensed MIT. It adds 88 tokens to every session and 893 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 2026-08-31.
Other skills, from other repositories
jetson-video-pipeline
Use when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or concise acceptance workflows.
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.
volt-ota
Produce a complete OTA update system design — partition layout, update flow, rollback conditions, validation checks, fleet management approach, failure modes and recovery. Use when asked about "OTA updates", "firmware updates over the air", "how do I update devices in the field", "OTA strategy", or "remote firmware…
proof-e2e
Build E2E test specs for critical user journeys — Playwright or Cypress, page objects, setup/teardown, CI config. Use when asked to "write E2E tests", "end-to-end testing", "browser tests", "UI tests", or "Playwright tests".
volt-firmware
Produce a complete firmware architecture spec for a described device — layer diagram, module responsibilities, HAL interface definitions, key state machines, RTOS decision. Use when asked to "design firmware architecture", "plan embedded firmware", "architect an IoT device", "how should I structure this firmware", or…