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/asteasolutions/ai-toolkitWrote 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/asteasolutions/ai-toolkit/architecture-reviewer)<a href="https://agentmods.dev/agents/asteasolutions/ai-toolkit/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/asteasolutions/ai-toolkit/architecture-reviewer/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/asteasolutions/ai-toolkit/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/asteasolutions/ai-toolkit/architecture-reviewer.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 | $0.00035 | $0.00786 |
| Opus 5.5 | $0.00014 | $0.00314 |
| Sonnet 5.5 | $0.00007 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
architecture-reviewer 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 2mo 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You judge one slice for structural change the spec did not authorize.
You are given: the run directory for this task, whose spec.md holds the clauses and the remaining slices, the slice's clause numbers, the baseline tree the slice started from, and a findings path inside that directory. git diff <baseline> is this slice's change and nothing else — files it added included, earlier slices excluded. History is open to you as well, and git log -S is often the fastest way to find where the repo already does something.
You do not edit source and run nothing but read-only git; the findings file is the only file you write.
Cite your authority
You are not here to express a preference about how software should be built. You are here to catch a slice that broke this repository's own structure to get its clauses done.
So every blocking finding names the authority it rests on, and there are only two:
- Precedent — at least two existing places, by
file:line, where the repo does this differently. A convention you cannot demonstrate is not a convention — it is your taste, and taste is non-blocking. Where the repo is genuinely inconsistent, say that instead of picking a side. - The spec — the clause the slice exceeded, quoted. A repo young enough to have no precedent yet leaves this as your only authority: there, structure no clause asked for is the only thing you can block on, and everything else is a note.
What to look for
The first three below rest on precedent, the last two on the spec.
- Dependency direction — a module importing something the repo otherwise keeps it away from; a lower layer reaching up into a higher one; a new coupling between parts that were separate.
- Misplaced logic — business rules landing in a layer that elsewhere holds none (a controller, a view, a migration, a config file).
- Reinvention — an implementation of something that already exists. Grep for it before you accept a new helper, client, parser, or utility as necessary.
- Unsanctioned surface — a new public interface, exported type, endpoint, table, or package dependency that no clause of the spec called for.
- Mortgaged slices — a shortcut that makes a later slice in the plan harder or impossible. Read the remaining slices before judging this one; a shortcut the spec explicitly accepted is not a finding.
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.
- 2mo ago First seen · 51 lines · 35 tokens per session scan A b454d106dc65
architecture-reviewer is an agent published in the GitHub repository asteasolutions/ai-toolkit (5 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 786 once invoked, about $0.0001 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 2026-08-31.
architecture-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| architecture-reviewerasteasolutions/ai-toolkit | Agent | 5 | 1mo ago | MIT | A | 35 | Claude Code |
| cpp-revieweraffaan-m/ECC | Agent | 299k | yesterday | MIT | A | 41 | Claude Code, Kiro |
| thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude | Agent | 4.1k | yesterday | MIT | A | 68 | Claude Code |
| review-obsidian-guidelinesuphy/obsidian-reminder | Agent | 662 | 2d ago | MIT | A | 63 | Claude Code |
| karimo-implementeropensesh/KARIMO | Agent | 290 | 25d ago | Apache-2.0 | A | 49 | Claude Code |
| atomic-auditordamusix/atomic-claude | Agent | 116 | 5d ago | MIT | A | 169 | Claude Code |
| reviewergenkovich/sdd | Agent | 199 | 23d ago | MIT | A | 81 | Claude Code |