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/cdeust/ai-architect-mcpWrote 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/cdeust/ai-architect-mcp/verify-architecture)<a href="https://agentmods.dev/commands/cdeust/ai-architect-mcp/verify-architecture"><img src="https://agentmods.dev/badge/commands/cdeust/ai-architect-mcp/verify-architecture/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/cdeust/ai-architect-mcp/verify-architecture"><img src="https://agentmods.dev/badge/commands/cdeust/ai-architect-mcp/verify-architecture.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 | $0.00017 | $0.00320 |
| Opus 5 | $0.00009 | $0.00160 |
| Sonnet 5 | $0.00003 | $0.00064 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
verify-architecture 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 8d 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.
What it actually says
Verify Architecture
Step 1 — Load Stage 7 skill
Read the verification skill:
Read skills/stage-7-verification/SKILL.md
This defines the deterministic verification stage — 64 HOR rules, build gate, graph verification. No LLM calls.
Step 2 — Run HOR rules
ai_architect_run_hor_rules(document={codebase_content}, categories=["all"])
This runs all 64 deterministic rules across 10 categories:
- Core PRD Structural (23 rules)
- Architecture & Code Quality (7 rules)
- Security (8 rules)
- Data Protection & Compliance (6 rules)
- Error Handling & Resilience (5 rules)
- Concurrency & State Management (3 rules)
- Senior Code Quality Standards (6 rules)
- Comprehensive Testing (6 rules)
- Observability & Monitoring (4 rules)
- Dependency & Supply Chain (2 rules)
Step 3 — Run verification scripts
scripts/verify-all.sh
This calls all verification scripts: zero-tolerance, swift-rules, 3rs, naming, claude-rules, production-tests, skill, security.
Step 4 — Report
Report pass/fail per rule category with compound score. If $ARGUMENTS specifies a path, verify only that path.
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.
- 8d ago First seen · 49 lines · 17 tokens per session scan A 0b5b5af6b4ad
verify-architecture is a command published in the GitHub repository cdeust/ai-architect-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 320 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
api
Debug API and data flow issues by tracing through Component -> TanStack Query -> Express Route -> Service -> SQLite/JSONL.
logs
Analyze server logs to diagnose errors, exceptions, and unexpected behavior.
cleanup
Comprehensive code cleanup using Knip and best practices for codebase maintenance.
data
Inspect database and state files to debug data issues.
performance
Diagnose performance issues including slow renders, bundle size, N+1 queries, and memory leaks.
browser
Debug and fix browser issues by inspecting, diagnosing, and resolving visual or technical problems.