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 yugash007/edu-agent-skills --skill architecture-reviewgit clone --depth 1 https://github.com/yugash007/edu-agent-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/yugash007/edu-agent-skills/architecture-review)<a href="https://agentmods.dev/skills/yugash007/edu-agent-skills/architecture-review"><img src="https://agentmods.dev/badge/skills/yugash007/edu-agent-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/yugash007/edu-agent-skills/architecture-review"><img src="https://agentmods.dev/badge/skills/yugash007/edu-agent-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 | $0.00029 | $0.00715 |
| Opus 5 | $0.00015 | $0.00358 |
| Sonnet 5 | $0.00006 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00072 |
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Evaluate a system design through structured probing that surfaces the learner's reasoning before prescribing corrections. Review across five dimensions: correctness, scalability, reliability, maintainability, observability.
Activation
- Learner proposes a design or architecture.
build-with-mereaches architecture phase. Learner asks "is this design good?" Interview prep on system design. Pre-deployment review. - Skip if: no design exists yet → use
teach-conceptorbuild-with-meto help create one. Design is a simple script with no architectural decisions. - Routing: if foundational concept gap blocks review → pause and route to
teach-conceptfirst. After review, hand off tobuild-with-mefor implementation orchallenge-generatorfor design alternatives.
Inputs
- Design proposal (diagram, description, or code), system constraints (scale, latency, team), learner level and goals.
Review Dimensions
- Correctness: does it solve the stated problem? Data integrity? Security?
- Scalability: bottlenecks at 10×, 100× current load?
- Reliability: single points of failure? Failure recovery? Data loss risk?
- Maintainability: complexity growth? Team onboarding? Testing surface?
- Observability: monitoring, alerting, debugging at runtime?
Workflow
- Strengths — Identify and state 2–3 things the design does well. Never start with criticism.
- Probe — 2–3 targeted questions exposing untested assumptions. Focus on the dimension where the design is weakest. Require learner reasoning before revealing issues.
- Issues — After learner responds: list issues priority-ordered by severity (Critical → Major → Minor). Each issue: dimension, description, severity.
- Alternatives — For each Critical/Major issue: propose 2 options with tradeoffs. Ask learner to choose with rationale.
- Revision — Summarize the agreed changes. Provide a short checklist of concrete next steps.
Rules
- DO: probe before prescribing — require learner reasoning first.
- DO: strengths first — never open with criticism.
- DO: alternatives with tradeoffs, not single "correct" answers.
- DO: pause review and route to
teach-conceptif a foundational concept gap blocks understanding. - DON'T: rewrite the design for the learner — coach them to revise it.
- DON'T: skip Critical issues to keep the session positive.
- DON'T: grade every dimension equally — focus on the weakest 2–3.
- DON'T: continue review when a fundamental security or correctness flaw needs conceptual teaching first.
What ships with it
2 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.
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 · 62 lines · 29 tokens per session scan A a4cd1b902ffb
architecture-review is a skill published in the GitHub repository yugash007/edu-agent-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 715 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
kotlin-review
Review Kotlin tests, architecture, or ABI compatibility, over the working tree, a commit, a pull request, or the whole repository.
install-codex-agents
Install this plugin's Kotlin review agents into Codex, which cannot load agents from a plugin.
Architecture Reviewer
Architecture Reviewer delivers production-grade technical work with clear architecture, tests, maintainability, and operational awareness.
call-codex
Use when the codex CLI should be driven from the agent — as a reviewer giving a second, independent opinion ("ask codex", "call codex", "codex review", "get a second opinion", "challenge this finding"), or as an executor doing a scoped task in the repository ("have codex do this", "delegate this to codex", "let codex…
minimalist-audit
Audit a codebase or directory for deletion candidates: dead code, unused dependencies, single-use abstractions, config that never varies, and duplicated helpers. Use when the user says "minimalist audit" or asks what can be deleted from a project.
minimalist-review
Review code, a diff, or a PR strictly for bloat: unrequested abstractions, dead scope, dependency creep, symptom-patching, and drive-by changes. Use when the user says "minimalist review", asks "is this over-engineered?", or wants a leanness review of a change.