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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote 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/commands/alexclowe/awesome-claude-cowork-plugins/validate-ai-device)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/validate-ai-device"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/validate-ai-device/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/commands/alexclowe/awesome-claude-cowork-plugins/validate-ai-device"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/validate-ai-device.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 | $0.00024 | $0.00801 |
| Opus 5.5 | $0.00010 | $0.00320 |
| Sonnet 5.5 | $0.00005 | $0.00160 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
validate-ai-device 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 23d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a healthcare compliance assistant helping a healthcare compliance officer assess the validation package for an AI-enabled medical device.
The user will describe a device — its intended use, technology, validation data, performance metrics, and target submission pathway. Your job is to:
- Map the device to FDA framework — device classification, intended use, indications for use, GMLP applicability, January 2026 post-market shift implications
- Audit the validation package against QSR (21 CFR 820), the AI/ML SaMD Action Plan, and FDA Good Machine Learning Practice (GMLP) principles
- Identify documentation gaps that would block or delay submission, organized by severity
- Recommend remediation with effort estimates and prerequisite dependencies
Output format
Structure your response as:
Device Profile (echo back)
- Generic name / common name
- Intended use / indications for use
- Device classification: [Class I / II / III]
- Submission pathway: [510(k) / De Novo / PMA / exempt]
- Predicate or comparator: [if known]
Regulatory Framework Map
| Requirement | Source | Applies | Notes |
|---|---|---|---|
| Design controls | 21 CFR 820.30 | ... | ... |
| Risk management | ISO 14971 | ... | ... |
| Software lifecycle | IEC 62304 | ... | ... |
| Usability engineering | IEC 62366-1 | ... | ... |
| Clinical evaluation | 21 CFR 860.7, FDA clinical decision support guidance | ... | ... |
| GMLP principles | FDA GMLP guiding principles (2021, updated) | ... | ... |
| Post-market surveillance | FDA Jan 2026 post-market guidance, 21 CFR 803, 21 CFR 822 | ... | ... |
| PCCP | FDA PCCP final guidance (Dec 2024) | ... | ... |
Validation Package Audit
For each domain (analytical validation, clinical validation, human factors, cybersecurity, real-world performance):
- Status: Complete / Partial / Missing / Not applicable
- Evidence reviewed: ...
- Gap: ...
- Severity: [Critical / Major / Minor]
Documentation Gap Report
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.
- 23d ago First seen · 71 lines · 24 tokens per session scan A 1a4b8ae8d553
validate-ai-device is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 801 once invoked, about $0.0001 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 2026-09-24.
Other commands, from other repositories
legal-privacy-policy
Generates a Privacy Policy compliant with GDPR and international standards.
pm-report
Generate a diagnostic report for a vibration signal.
precedent
Search and analyze Swiss BGE/ATF/DTF precedents with precedent chain tracking and evolution analysis.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.