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 agentmods add skills/bnet47/codexicon/architecture-reviewnpx skills add bnet47/codexicon --skill architecture-reviewgit clone --depth 1 https://github.com/bnet47/codexiconWrote 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/bnet47/codexicon/architecture-review)<a href="https://agentmods.dev/skills/bnet47/codexicon/architecture-review"><img src="https://agentmods.dev/badge/skills/bnet47/codexicon/architecture-review.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00486 |
| Opus 5 | $0.00014 | $0.00243 |
| Sonnet 5 | $0.00006 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
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 5d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture review
Announce: "I'm using architecture-review to evaluate this decision and record its consequences."
1. Load decision context
Read relevant accepted ADRs, agent_docs/architecture.md, project constraints, and the code that establishes the current system. If an ADR already settles the question, surface it and determine whether new evidence justifies superseding it.
2. Research only unstable facts
For current libraries, platform capabilities, pricing, limits, or deprecations, use a read-only researcher and primary sources. Do not browse merely to validate general engineering principles.
3. Define decision drivers
State the decision, constraints, non-negotiable qualities, and observable signals that would make the choice fail. Evaluate two or three viable options against the drivers most relevant here, normally including:
- product and constraint fit;
- operational complexity and failure isolation;
- security and data ownership;
- reversibility and migration cost;
- delivery and ongoing cost;
- testability, observability, and agent/developer navigability.
Avoid false precision. Use qualitative ratings unless reliable measurements exist.
4. Recommend and obtain direction
Lead with the recommended option, its decisive reason, and its largest downside. Ask the user only when the choice changes product behavior, cost, or irreversible commitments beyond the authority already granted.
5. Record the ADR only when authorized
If the user asked only for advice, a comparison, or a review, return the recommendation without modifying the repository. Create or update architecture documents only when the user asked to record the decision, asked for implementation that includes the decision, or explicitly delegated repository changes.
Copy docs/adr-template.md to the next available agent_docs/decisions/ADR-NNN-[slug].md.
- Use
Status: Proposedwhen a required human decision is pending. - Use
Status: Acceptedwhen the user chose the option or explicitly delegated the decision. - Link any superseded ADR from the new record; do not rewrite the accepted historical decision.
- Update
agent_docs/architecture.mdwhen the accepted choice changes system shape.
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.
- 5d ago First seen · 48 lines · 28 tokens per session scan A bfa3ec8d5c65
architecture-review is a skill published in the GitHub repository bnet47/codexicon (5 stars, last pushed 6d ago), licensed MIT. It adds 28 tokens to every session and 486 once invoked, about $0.0001 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
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
当用户需要对PDF文件进行任何操作时，请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF，请使用此技能。.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
oma-hwp
Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts text, headings, tables, lists, images, footnotes, and hyperlinks. Use for Korean word processor files (Hangul), government documents, and AI-ready data preparation.
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.