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 DominikTobureto/awesome-grok-build --skill architecture-reviewgit clone --depth 1 https://github.com/DominikTobureto/awesome-grok-buildWrote 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/dominiktobureto/awesome-grok-build/architecture-review)<a href="https://agentmods.dev/skills/dominiktobureto/awesome-grok-build/architecture-review"><img src="https://agentmods.dev/badge/skills/dominiktobureto/awesome-grok-build/architecture-review/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/dominiktobureto/awesome-grok-build/architecture-review"><img src="https://agentmods.dev/badge/skills/dominiktobureto/awesome-grok-build/architecture-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00387 |
| Opus 5 | $0.00017 | $0.00193 |
| Sonnet 5 | $0.00007 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
architecture-review 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.
What it actually says
Architecture Review
Design the smallest architecture that can survive the next real change.
Grok Build Mode
- Start in Plan Mode. Architecture work should not begin with edits.
- Use subagents for parallel discovery:
domain: core entities, use cases, invariants.data: persistence, schemas, migrations, ownership.interfaces: APIs, UI boundaries, jobs, integrations.risk: coupling, circular dependencies, deployment constraints.
- Arena-style design: compare 2-3 architecture options and rank by reversibility, simplicity, and testability.
- Human-in-the-loop: ask for approval before introducing new layers, packages, services, or dependencies.
Workflow
- Clarify the product/job-to-be-done.
- Map current modules and data flow.
- Identify constraints: runtime, team, deploy, scale, compliance.
- Propose options:
- minimal change;
- modular boundary;
- larger redesign if justified.
- Recommend one path with migration steps.
- Define tests and observability needed.
Architecture Rules
- Prefer modular boundaries over premature microservices.
- Keep dependency direction explicit.
- Put business rules where they can be tested without infrastructure.
- Avoid abstract factories/layers unless they remove real coupling.
- Write an ADR for major choices.
Example Prompts
Use architecture-review. Compare clean/hexagonal/modular approaches for this feature and recommend the smallest reversible plan.
Map the current data flow with subagents, identify coupling risks, and propose an ADR before edits.
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 · 52 lines · 34 tokens per session scan A 1d57967f1038
architecture-review is a skill published in the GitHub repository DominikTobureto/awesome-grok-build (61 stars, last pushed 19d ago), licensed MIT. It adds 34 tokens to every session and 387 once invoked, about $0.0002 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
cua-driver
Drive a native GUI app (macOS, Windows, Linux) via the Qwen Cua Driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive…
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
workflow-authoring
Reference for writing a Workflow tool script (script API and gotchas, agent() options, pipeline() vs parallel(), verification and convergence patterns, resume, worked example). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.
goal-draft
Turn a fuzzy intention into a /goal objective the Goal verifier can actually judge - one outcome, numbered binary "Done when" checks that leave evidence in the transcript, guardrails, a budget, and a block protocol. Use when the user wants to set or define a goal, asks whether a goal is good enough, or says "keep…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
tmux-real-user-testing
A real-user test workflow for Qwen Code's terminal interface, using tmux to drive the program and capture readable screen snapshots. tmux is a tool for running and observing terminal sessions.