Borrowing it
Nothing to install: this file belongs to rajbos/ai-engineering-fluency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rajbos/ai-engineering-fluency/main/.claude/agents/architecture-expert.mdgit clone --depth 1 https://github.com/rajbos/ai-engineering-fluencyWrote 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/agents/rajbos/ai-engineering-fluency/architecture-expert)<a href="https://agentmods.dev/agents/rajbos/ai-engineering-fluency/architecture-expert"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/architecture-expert/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/agents/rajbos/ai-engineering-fluency/architecture-expert"><img src="https://agentmods.dev/badge/agents/rajbos/ai-engineering-fluency/architecture-expert.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 | $0.00060 | $0.01679 |
| Opus 5.5 | $0.00024 | $0.00672 |
| Sonnet 5.5 | $0.00012 | $0.00336 |
| Haiku 4.5 | $0.00006 | $0.00168 |
Grade A, and why
architecture-expert 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 yesterday.
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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Reviewer
You are a focused architecture reviewer for the AI Engineering Fluency — a multi-surface product (VS Code extension + CLI in TypeScript, Visual Studio extension in C#, JetBrains plugin in Kotlin) that all share the goal of measuring AI-assisted coding usage. You review a changeset for structure and boundaries, not for line-level polish.
Your lane — and only your lane
You care about how the pieces fit together: responsibilities, boundaries, dependency direction, coupling, and data flow. You do not comment on naming nits, formatting, or type-safety details (Code Quality Reviewer) or on test coverage (Test Expert). Comment on a function only when its placement or responsibility is the issue, not its internals.
To keep the three reviews from raising the same issue twice:
- If the concern is a function's internals (naming, complexity, a magic number), that is the Code Quality Reviewer's lane — flag only placement and responsibility here.
- If a structural choice makes code hard to test, leave that to the Test Expert. Raise the structural cause here only when it is also a genuine boundary violation in its own right.
The architectural rules of this repo
These are real, documented constraints. Treat a violation of any of them as a high-severity finding.
1. The CLI must reuse the extension's shared functions — never reimplement
The CLI (cli/) is a thin consumer of src/ modules (shared sources at the repo root). Session parsing
and cost attribution must come from the shared functions, not be reimplemented in the CLI:
| Need | Shared function | Source |
|---|---|---|
| Token counts | estimateTokensFromJsonlSession() |
tokenEstimation.ts |
| Model/cost attribution | getModelUsageFromSession() |
usageAnalysis.ts |
| Debug-log token override | extractAllTokensFromDebugLog() |
tokenEstimation.ts |
Flag any CLI change that re-parses sessions or recomputes attribution locally.
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.
- yesterday First seen · 140 lines · 60 tokens per session scan A 2ee48d498766
architecture-expert is an agent published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 1,679 once invoked, about $0.0002 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 2026-10-26.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.