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 cniska/skills --skill architecture-reviewgit clone --depth 1 https://github.com/cniska/skillsWrote 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/cniska/skills/architecture-review)<a href="https://agentmods.dev/skills/cniska/skills/architecture-review"><img src="https://agentmods.dev/badge/skills/cniska/skills/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/cniska/skills/architecture-review"><img src="https://agentmods.dev/badge/skills/cniska/skills/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 | $0.00025 | $0.00987 |
| Opus 5 | $0.00013 | $0.00494 |
| Sonnet 5 | $0.00005 | $0.00197 |
| Haiku 4.5 | $0.00003 | $0.00099 |
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 12d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Review
Review architecture quality, design consistency, extension seams, and pattern adherence.
Scope
1. Indirection pressure (primary focus)
Flag layers that add no architectural value:
- runtime import cycles across split modules
- pass-through facades that only rename or re-export
- alias/wrapper layers without independent policy or invariants
- DI bags exceeding practical seam or testing needs
- singleton imports in library modules that should accept injected params — an application reading its own central store is idiomatic and not this finding
- facade-for-facade chains
Default: if a layer carries no policy, invariants, or boundary isolation, remove it.
2. Extension blockers
- hard-coded behavior where project docs or an existing sibling seam establish a policy/config point
- new features requiring edits across many unrelated modules
- private coupling preventing additive providers or plugins
- extension seams with no current use adding maintenance cost
3. Boundary and contract integrity
- contracts and schemas as source of truth
- renamed contract terms stay aligned across the boundary; partial renames count as drift
- dependency direction consistency
- design-pattern consistency for extension seams
- logic that reads another module's state more than its own; judge one function body at a time — how much of it traverses that module — not by whether the reference was injected or passed in
- chained access (
a.getB().getC()) reaching past a stated contract into internals the caller doesn't own - modules reaching into each other's internals instead of through a stated contract
4. Cohesion and responsibility
- oversized or multi-responsibility files — for a file, size alone isn't the finding, so name the second responsibility or don't report it
- SRP violations: mixing unrelated concerns
- at function scale length is a finding on its own: a body past ~50 lines, one needing section comments to navigate, or one that computes a result and then formats it for presentation. An exhaustive match or switch whose length is entirely its arms is not this — there is no substructure to lift out
- duplication wants a name once it is a substantial block repeated twice or a small one repeated three times, in one file or across modules — size and copy count trade off against each other, so a two-line body appearing seven times counts. Leave what is duplicated on purpose: boundary-local copies keeping two modules independent, and conditionally-compiled twins that merging would defeat
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.
- 12d ago First seen · 89 lines · 25 tokens per session scan A ee790f82d236
architecture-review is a skill published in the GitHub repository cniska/skills (5 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 987 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…