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/nxtg-ai/forge-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/commands/nxtg-ai/forge-plugin/compliance)<a href="https://agentmods.dev/commands/nxtg-ai/forge-plugin/compliance"><img src="https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/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/commands/nxtg-ai/forge-plugin/compliance"><img src="https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/compliance.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 | $0.00012 | $0.01044 |
| Opus 5.5 | $0.00005 | $0.00418 |
| Sonnet 5.5 | $0.00002 | $0.00209 |
| Haiku 4.5 | $0.00001 | $0.00104 |
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 12d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NXTG-Forge Compliance Check
You are the Compliance Auditor - scan the project's dependency tree for license compatibility and generate a Software Bill of Materials.
Parse Arguments
Arguments received: $ARGUMENTS
Options:
- No arguments: Full compliance report
--sbom: Generate CycloneDX SBOM and save to .claude/reports/--json: Output raw JSON instead of formatted report--conflicts-only: Show only license conflicts--fix: Suggest replacements for problematic dependencies
Step 1: Tech Stack Inventory
Read package.json in the project root to get:
- Project name, version, license
- Count dependencies vs devDependencies
- Identify key frameworks (react, express, vite, etc.)
Run:
node --version
npm --version
Step 2: Dependency License Scan
Run:
npm ls --json --all --long 2>/dev/null
For each dependency, check license compatibility with project license (MIT):
COMPATIBLE (no action needed): MIT, ISC, BSD-2-Clause, BSD-3-Clause, Apache-2.0, 0BSD, Unlicense, CC0-1.0, BlueOak-1.0.0, Python-2.0
CONDITIONAL (acceptable, note in report): LGPL-2.1, LGPL-3.0, MPL-2.0
INCOMPATIBLE (flag as conflict): GPL-2.0-only, GPL-3.0-only, AGPL-3.0, SSPL-1.0, EUPL-1.2
UNKNOWN (needs investigation): Missing license, custom license, NOASSERTION
For each dependency in the npm ls output, also read:
cat node_modules/{dep-name}/package.json | grep -i license
to get the license field (npm ls doesn't always include it).
Step 3: Compliance Score
Calculate score (0-100):
- Start at 100
- -0 per compatible dep
- -2 per conditional dep
- -10 per incompatible production dep
- -5 per incompatible dev dep
- -3 per unknown license
Step 4: Display Report
Format:
NXTG-Forge Compliance Report
============================
Generated: {timestamp}
PROJECT
Name: {name} v{version}
License: {license}
Node: {node_version}
TECH STACK
Runtime: {frameworks list}
Languages: TypeScript, JavaScript
Dependencies: {prod_count} production, {dev_count} development
LICENSE SCAN
Compliance Score: {score}/100 [{PASS|WARN|FAIL}]
Compatible: {count} deps
Conditional: {count} deps
Incompatible: {count} deps
Unknown: {count} deps
{If conflicts exist:}
LICENSE CONFLICTS
[{severity}] {dep_name}@{version} - {license}
Risk: {explanation}
Action: {recommendation}
{If --sbom:}
SBOM
Format: CycloneDX 1.5 JSON
Components: {count}
Saved to: .claude/reports/sbom-{date}.json
---
Quick Actions:
/nxtg-forge:compliance --sbom Generate SBOM file
/nxtg-forge:compliance --fix Suggest replacements
/nxtg-forge:deploy --validate-only Pre-deploy validation
/nxtg-forge:gap-analysis --scope security Security gap analysis
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.
- 12d ago Changed d2306ce35841
- 1mo ago Changed · +13 lines · +12 tokens per session 53305103df05
- 1mo ago First seen · 130 lines · 0 tokens per session scan A 36585019e137
compliance is a command published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 1,044 once invoked, about $0.0000 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 commands, from other repositories
data-policy
Documentar qué datos toca el framework, qué sale a APIs externas y generar política de privacidad. Usa cuando el usuario dice "data policy", "política de datos", "privacy policy", "datos sensibles", "GDPR", "data handling", "APIs externas", "external APIs", "qué datos se comparten". Mapea data flows y genera política…
audit-trail
Generar y consultar el log de auditoría de decisiones asistidas por IA. Usa cuando el usuario dice "audit trail", "decision log", "log de decisiones", "AI decisions", "audit log", "追溯", "track decisions", "quien decidió qué", "decision history". Registra y consulta el log de decisiones tomadas durante la sesión.
appstore-review
Run a quick App Store compliance check. Faster than full audit, focuses on most common rejection reasons.
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
review-policy
Review a policy document for structure, coverage, and language quality.