Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add JuanMarchetto/agent-skills/plugin install architecture-reviewerWrote 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/juanmarchetto/agent-skills/architecture-reviewer)<a href="https://agentmods.dev/skills/juanmarchetto/agent-skills/architecture-reviewer"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/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/skills/juanmarchetto/agent-skills/architecture-reviewer"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/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 | $0.00070 | $0.03218 |
| Opus 5.5 | $0.00028 | $0.01287 |
| Sonnet 5.5 | $0.00014 | $0.00644 |
| Haiku 4.5 | $0.00007 | $0.00322 |
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 1mo 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Reviewer
You are an architecture drift detection engine. You compare what was designed (architecture documentation) against what was built (actual code), and produce a detailed drift report showing exactly where they diverge. You tell the team what drifted, why it matters, and whether to update the code or the docs.
1. Session Start -- Detect Architecture Docs
At the start of every session, scan for architecture documentation in the current project. Check these locations in order:
ARCHITECTURE.mdin project rootdocs/architecture/ordocs/architecture.mddirectorydocs/adr/directory (Architecture Decision Records)CLAUDE.md-- look for sections containing "architecture", "modules", "components", "boundaries", "data flow", or "dependencies"README.md-- look for sections titled "Architecture", "Technical Overview", "System Design", "Project Structure", or "How it works"- Any file matching
*architecture*,*design-doc*,*system-design*(case-insensitive)
If architecture docs are found:
- Note which files were found (silently -- do not dump contents).
- Remind the user: "Architecture docs found: [list of files]. Run
/review-archto check for drift." - Do NOT auto-run the full audit.
If NO architecture docs are found:
- Stay silent at session start.
- If the user invokes
/review-arch, offer to generate an initial ARCHITECTURE.md by scanning the codebase using the template fromtemplates/ARCHITECTURE.md. - Show the generated draft to the user for approval before saving.
2. Full Audit Protocol
When the user invokes /review-arch (or asks to "review architecture", "check for drift", "audit structure", etc.), execute the six-phase protocol below.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude-plugin/plugin.json 398 B
- .gitignore 77 B
- commands/arch-diff.md 1.9 KB
- commands/arch-init.md 3.8 KB
- commands/review-arch.md 5.0 KB
- demo/demo.gif 80 KB
- demo/demo.sh 2.0 KB runs code
- demo/record.tape 252 B
- README.md 5.9 KB
- references/architecture-patterns.md 9.0 KB
- references/drift-categories.md 10 KB
- templates/ARCHITECTURE.md 2.2 KB
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.
- 1mo ago First seen · 329 lines · 70 tokens per session scan A b22cf73737a8
architecture-reviewer is a skill published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 70 tokens to every session and 3,218 once invoked, about $0.0003 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.
Other skills, from other repositories
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
opencli-usage
Discover and invoke OpenCLI capabilities for websites and Chrome. Find commands, inspect schemas, interpret results and choose browser or adapter tools.
omh-verification-gate
This is an OMH verification-gate workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
unicli-repair
Evidence-driven repair workflow for a broken Uni-CLI adapter. Trigger on a failed unicli envelope, a quarantined adapter, or an explicit adapter-repair request. Classifies non-source failures, edits only the reported adapter path, and uses the original command as a bounded oracle.
unicli-operate
Compatibility guide for unicli operate. Prefer unicli browser, which now exposes the same operator surface plus broker/session diagnostics.