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 korbinjoe/TeemAI --skill architecture-reviewgit clone --depth 1 https://github.com/korbinjoe/TeemAIWrote 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/korbinjoe/teemai/architecture-review)<a href="https://agentmods.dev/skills/korbinjoe/teemai/architecture-review"><img src="https://agentmods.dev/badge/skills/korbinjoe/teemai/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/korbinjoe/teemai/architecture-review"><img src="https://agentmods.dev/badge/skills/korbinjoe/teemai/architecture-review.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 | $0.00062 | $0.03890 |
| Opus 5 | $0.00031 | $0.01945 |
| Sonnet 5 | $0.00012 | $0.00778 |
| Haiku 4.5 | $0.00006 | $0.00389 |
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 10d 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 — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Dimension Framework (9-Dimension Review Model)
1. Layered Architecture & Separation of Concerns
Review goal: Whether each layer has clear responsibility definitions, whether cross-layer leakage exists.
- Does the presentation layer (UI) contain business logic or data access?
- Does the business layer directly manipulate DOM or depend on UI frameworks?
- Does the data layer leak into the presentation layer (e.g., components directly building SQL/API paths)?
- Are there "god modules" (single file > 500 lines, single directory > 20 direct child files)?
- Do layers communicate through explicit interface/type contracts?
Detection method:
Scan directory structure → identify layering pattern → check cross-layer imports → flag violations
2. Module Boundaries & Cohesion
Review goal: Whether modules are reasonably divided by domain/function, with high internal cohesion and low external coupling.
- Does directory structure reflect domain division (organized by feature vs by technical type)?
- Are there "junk drawer" directories (utils/helpers/common bloating into boundaryless catch-alls)?
- Is the module's public API minimized (only necessary interfaces exported via index.ts)?
- Are there direct references to internal implementations across modules (bypassing public API)?
- Is the same concept scattered across multiple unrelated directories?
Detection method:
Analyze import graph → calculate module Fan-in/Fan-out → identify high-coupling hotspots
3. Dependency Governance
Review goal: Whether dependency direction is reasonable, whether circular or implicit dependencies exist.
- Does dependency direction satisfy the "Stable Dependencies Principle" (high-level depends on low-level, not reverse)?
- Are there circular dependencies (A → B → C → A)?
- Are there cross-boundary dependencies (frontend directly importing backend internal modules, private paths in shared node_modules)?
- Do third-party dependencies have an isolation layer (directly scattered in business code vs encapsulated in adapter/wrapper)?
- Do key dependencies (xterm.js, Express, Electron) have a replacement/upgrade 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.
- 10d ago First seen · 417 lines · 62 tokens per session scan A e516a5b8fd99
architecture-review is a skill published in the GitHub repository korbinjoe/TeemAI (2 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 3,890 once invoked, about $0.0003 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 skills, from other repositories
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.
reflecting-findings
Use when a reflection package hands you another agent's review findings to verify (before they become a fix request): you are the REFLECTOR, an independent skeptic. Judge each finding against the real code and settle it with reflectfinding — kept or refuted.
azure-repos
Expert knowledge for Azure Repos development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when managing Git/TFVC repos, branch/PR policies, CLI/IDE integrations, CodeQL/scanning, or…
performance-review
A code audit that checks changed Go code against documented performance rules, especially code used frequently or on request paths.
concurrency-review
A code review procedure that checks whether concurrent code can safely share data and perform operations at the same time. Concurrency means multiple parts of a program run in overlapping periods.
io-review
A code-audit guide for checking database and service input/output patterns against documented rules. It looks for unnecessary repeated queries, N+1 queries, and independent operations run one after another.