llmops-demo-ts: Skill for Claude Code

.claude/skills/compliance-check/SKILL.md

compliance-check is a skill for Claude Code from yu-iskw/llmops-demo-ts. It costs 30 tokens per session (347 once invoked), scanned A, original, Apache-2.0.

A compliance review skill that checks software licences, privacy and personal-data handling, and ethical safeguards for AI features. It examines dependencies, data sent to outside AI services, retention, input and output filtering, and possible bias.

In plain words
What is it for?
It is for reviewing dependency licences, tracing data flows, checking personal information handling, and assessing safeguards around AI agents.
Why use it?
It helps reveal legal or privacy problems before new libraries, user data, or AI services are added. It also turns the review into a report with a status and action list.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: agent in frontmatter.

This is yu-iskw/llmops-demo-ts's own configuration. It tells Claude Code how to work on llmops-demo-ts itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llmops-demo-ts configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yu-iskw/llmops-demo-ts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yu-iskw/llmops-demo-ts/main/.claude/skills/compliance-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/yu-iskw/llmops-demo-ts

Made for: Claude Code.

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 compliance-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/yu-iskw/llmops-demo-ts/compliance-check/github.svg)](https://agentmods.dev/skills/yu-iskw/llmops-demo-ts/compliance-check)
Your own site
<a href="https://agentmods.dev/skills/yu-iskw/llmops-demo-ts/compliance-check"><img src="https://agentmods.dev/badge/skills/yu-iskw/llmops-demo-ts/compliance-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 compliance-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/yu-iskw/llmops-demo-ts/compliance-check"><img src="https://agentmods.dev/badge/skills/yu-iskw/llmops-demo-ts/compliance-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 347 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 $0.00030 $0.00347
Opus 5 $0.00015 $0.00173
Sonnet 5 $0.00006 $0.00069
Haiku 4.5 $0.00003 $0.00035

Measured 6d ago against content hash 3268b1759751, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

compliance-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 6d 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.

.claude/skills/compliance-check/SKILL.md · 60 lines

What it actually says

Compliance Check

Perform a compliance check with the following scope:

$ARGUMENTS

Compliance Checks

License Compatibility

  1. List all project dependencies and their licenses
  2. Verify compatibility with the project's ISC license
  3. Flag any copyleft (GPL, AGPL) or restrictive licenses
  4. Check for attribution requirements

Data Privacy

  1. Trace user data flow through the application:
    • Frontend: What data is collected in forms?
    • Backend: What data is stored, logged, or forwarded?
    • Agents: What user data is sent to external AI APIs (Google Gemini)?
    • LangSmith: What data is sent for tracing/observability?
  2. Identify PII handling
  3. Check data retention practices

AI Ethics

  1. Review AI agent guardrails (secure_agent input/output sanitization)
  2. Check for content filtering mechanisms
  3. Verify transparency about AI-generated content
  4. Review for potential bias in agent behavior

Output

Produce a compliance report:

## Summary: [PASS / NEEDS ATTENTION / FAIL]

### License Compliance: [PASS/FAIL]
[Details]

### Data Privacy: [PASS/FAIL]
[Details]

### AI Ethics: [PASS/FAIL]
[Details]

### Action Items
1. [Priority-ordered list of required changes]
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. 6d ago First seen · 60 lines · 30 tokens per session scan A 3268b1759751

Subscribe to this mod's changes

compliance-check is a skill published in the GitHub repository yu-iskw/llmops-demo-ts (6 stars, last pushed 10d ago), licensed Apache-2.0. It adds 30 tokens to every session and 347 once invoked, about $0.0002 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 2026-09-04.