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/navraj007in/architecture-cowork-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/navraj007in/architecture-cowork-plugin/compliance)<a href="https://agentmods.dev/commands/navraj007in/architecture-cowork-plugin/compliance"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-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/navraj007in/architecture-cowork-plugin/compliance"><img src="https://agentmods.dev/badge/commands/navraj007in/architecture-cowork-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 | $0.00018 | $0.02803 |
| Opus 5 | $0.00009 | $0.01401 |
| Sonnet 5 | $0.00004 | $0.00561 |
| Haiku 4.5 | $0.00002 | $0.00280 |
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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/architect:compliance
Trigger
/architect:compliance [options]
Options:
[frameworks:sox2,hipaa,gdpr,pci]— specify which to audit (comma-separated; default: all applicable)[non_interactive:true]— skip all questions, derive from SDL
Purpose
Production systems need to comply with regulatory frameworks. This command scans your project for compliance gaps, produces a prioritized remediation plan, and documents the current control state. Covers SOC2 Type II, HIPAA, GDPR, and PCI DSS — mapping each framework's controls to code-level implementation patterns.
Workflow
Quick Navigation
| Phase | Steps |
|---|---|
| Setup | Step 1 · Step 1.5 |
| Analysis | Step 2 · Step 2.5 |
| Scanning | Step 3 · Step 3.5 |
| Completion | Step 4 · Step 4.5 · Step 5 |
Step 1: Read Context and Detect Frameworks
ℹ️ CONTEXT LOADING: _state.json → SDL → project structure
First, read architecture-output/_state.json if it exists. Extract:
project.name,project.stagetech_stack.backend,tech_stack.database(determines scope)- Any existing
compliancesection (if this is a re-audit)
Then, read SDL to detect compliance flags:
nonFunctional.security.compliance[]— list of applicable frameworks (SOC2, HIPAA, GDPR, PCI)nonFunctional.security.pii— does system handle Personally Identifiable Information?nonFunctional.security.phi— does system handle Protected Health Information (healthcare)?nonFunctional.security.pci— does system handle payment card data?
Check project structure:
- Look for existing compliance artifacts:
docs/compliance/,docs/security/, audit reports - Check for encryption implementations:
src/lib/encryption.ts,.envwith encryption keys - Look for audit logging:
src/lib/logger.ts,src/lib/auditLog.ts
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 First seen · 292 lines · 18 tokens per session scan A 36967bf0fe92
compliance is a command published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 2,803 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
service-auditor-prep
Generate complete auditor-ready evidence package for SOC 2.
soa-generator
Generate ISO 27001 Statement of Applicability (SOA) with control selection justifications.
breach-process
GDPR breach notification procedures and 72-hour requirement.
dpia
Data Protection Impact Assessment (DPIA) guidance and execution.
safeguards
Safeguards Rule implementation guidance.
impact-select
Determine appropriate StateRAMP impact level (Low vs Moderate).