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 VeryGoodOpenSource/vgv-ai-flutter-plugin --skill license-compliancegit clone --depth 1 https://github.com/VeryGoodOpenSource/vgv-ai-flutter-pluginWrote 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/verygoodopensource/vgv-ai-flutter-plugin/license-compliance)<a href="https://agentmods.dev/skills/verygoodopensource/vgv-ai-flutter-plugin/license-compliance"><img src="https://agentmods.dev/badge/skills/verygoodopensource/vgv-ai-flutter-plugin/license-compliance/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/verygoodopensource/vgv-ai-flutter-plugin/license-compliance"><img src="https://agentmods.dev/badge/skills/verygoodopensource/vgv-ai-flutter-plugin/license-compliance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 17 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00174 | $0.01787 |
| Opus 5 | $0.00087 | $0.00894 |
| Sonnet 5 | $0.00035 | $0.00357 |
| Haiku 4.5 | $0.00017 | $0.00179 |
Grade A, and why
license-compliance 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 today.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
License Compliance
Dependency license auditor for Dart and Flutter projects — verifies that all package dependencies use licenses compatible with the project's requirements using the Very Good CLI MCP tools.
Cross-harness fallback. On Claude Code the
packages_check_licensesMCP tool is the execution path. On a host without this plugin's Bash hooks and without the Very Good CLI MCP server connected, runvery_good packages check licenses <project-directory>directly (the target path is positional and defaults to.; add--dependency-type direct-main,transitiveso transitive obligations are covered) and read its output the same way — never block on a missing MCP server.
Core Standards
Apply these standards to ALL license compliance work:
- Run
packages_check_licensesMCP tool on the target project directory withlicenses: trueto display full license information - Pass
directoryto the MCP tool when the project is not at the workspace root — monorepos with the project in a subdirectory (e.g.mobile/) requiredirectory: 'mobile' - A missing license is not "no license" — it means "all rights reserved" by default; always flag
- Transitive dependencies matter — a permissive package that depends on a GPL package still carries the GPL obligation
- Only scan output can certify compliance — never conclude that a project is compliant, clear, or safe to ship from a pubspec dependency list, a package name, a remembered license, or a previous audit. Scan output the user pastes or attaches counts as scan output: take it at face value, audit it, and do not re-run it or question its provenance. The distinction is whether each package arrives with a license attached, not who produced the text
- Flag for manual review when in doubt — never assume compliance without a clear license identifier
- Deliver the report in the prescribed format — when scan output exists, the answer is the template in Report Findings: the
## License Compliance Reportheading, the summary counts including the total scanned, the flagged table with a risk level and a recommendation per row, and the ranked recommendations. A prose write-up or a bulleted list of packages is not the deliverable, however complete its content
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · +1 lines · +140 tokens per session 0c4a1d3f7120
- 9d ago First seen · 112 lines · 34 tokens per session scan A 0b479bb74c4c
license-compliance is a skill published in the GitHub repository VeryGoodOpenSource/vgv-ai-flutter-plugin (161 stars, last pushed today), licensed MIT. It adds 174 tokens to every session and 1,787 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
fsi-compliance-checker
Maps code, architecture, and infrastructure changes to specific control IDs in financial services compliance frameworks - PCI-DSS v4.0 for payment card data and MAS TRM for Singapore-regulated institutions - producing an audit-traceable findings report with per-control remediation. Use this instead of a general…
counseling-psychology
Therapeutic frameworks, assessment, ethical practice, and client documentation for counselors and psychologists.
apply-enforcement-timing
Use when misconduct, policy violation, or serious wrongdoing has been detected — to determine whether to act immediately or delay enforcement until the case is overwhelming and legally unassailable, because premature enforcement against powerful bad actors weakens the case, creates procedural exposure, and enables the…
design-speak-up-framework
Use when building or auditing your organization's ability to surface ethical violations, compliance breaches, safety issues, and misconduct — to design the channels, protections, and culture that make reporting wrongdoing possible and expected, because without explicit institutional design, fear of retaliation…
apply-borrowed-force
Use when you need to attack a target — competitor, policy, incumbent — that you cannot attack directly due to political, legal, reputational, or resource constraints, by enlisting third parties with their own genuine aligned interest.
apply-iso-31000-risk-framework
Use when an organization needs a systematic, repeatable process for managing risk broadly — establishing context, identifying risks, analyzing and evaluating them, treating the significant ones, and monitoring the whole process over time — rather than handling risk ad hoc through isolated, disconnected efforts (an…