compliance

An agent that checks a project for legal, privacy, accessibility, and coding-standard risks. Its checks include dependency licenses, GDPR data handling, WCAG 2.1 AA accessibility, and rules such as TypeScript strictness and test coverage.

In plain words
What is it for?
Use it to audit open-source dependency licenses, personal-data handling, accessibility requirements, and project coding standards.
Why use it?
It helps find compliance problems that may not appear as ordinary software bugs but can create legal, regulatory, or maintenance liabilities. It provides a review across several project-risk areas.

Agent

Install

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.

agentmods
npx agentmods add agents/nxtg-ai/forge-plugin/compliance
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,059 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02059
Opus 5 $0.00000 $0.01030
Sonnet 5 $0.00000 $0.00412
Haiku 4.5 $0.00000 $0.00206

Measured 2d ago against content hash aea3f4d0726f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

docs/agents/compliance.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compliance

Audits your project against legal, regulatory, and policy requirements -- dependency licenses, GDPR data handling, WCAG accessibility, and coding standards enforcement.

Level L1 Vibe Coder
Category Governance & Analysis
Model Haiku

What It Does

The Compliance agent protects your project from legal and regulatory risk. It audits dependency licenses for compatibility (is that GPL-3.0 package going to force your MIT project open-source?), checks data handling against GDPR requirements (do you have a data inventory? can users request deletion?), verifies WCAG 2.1 AA accessibility compliance (do all images have alt text? does keyboard navigation work?), and enforces coding standards (TypeScript strict mode, no any types, test coverage thresholds).

What makes this agent important is that compliance failures are not bugs -- they are liabilities. A GPL-3.0 dependency in an MIT-licensed project creates a legal obligation you might not discover until an audit. Personal data stored without a retention policy or deletion capability violates GDPR regardless of whether anyone has complained yet. Missing WCAG compliance excludes users with disabilities and exposes the project to ADA lawsuits in some jurisdictions. These are not theoretical risks; they are the specific risks the Compliance agent checks for.

Unlike the Security agent (which finds technical vulnerabilities) or the Guardian (which enforces code quality), the Compliance agent operates at the policy layer. It asks: "Is this project legally safe to distribute? Does it handle personal data lawfully? Is it accessible to all users? Does it follow its own stated standards?" These are questions that developers rarely ask during implementation but that become critical at release time.

When to Use It

  • Before a release: When you need to verify that all dependencies have compatible licenses, no GDPR violations exist, and accessibility standards are met.
  • After adding new dependencies: When new packages have been added and you need to verify their licenses are compatible with your project's license.
  • When handling user data: When you are implementing features that collect, store, or process personal information and need to verify GDPR compliance.
  • During accessibility reviews: When your project needs WCAG 2.1 AA verification and you want a systematic check of contrast ratios, keyboard navigation, ARIA labels, and semantic HTML.

Read the full file on GitHub · 144 lines

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. 2d ago First seen · 144 lines · 0 tokens per session scan A aea3f4d0726f

Subscribe to this mod's changes

compliance is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,059 tokens. 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.