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 onfire7777/universal-ai-skills-library --skill arc-design-reviewgit clone --depth 1 https://github.com/onfire7777/universal-ai-skills-libraryWrote 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/onfire7777/universal-ai-skills-library/arc-design-review)<a href="https://agentmods.dev/skills/onfire7777/universal-ai-skills-library/arc-design-review"><img src="https://agentmods.dev/badge/skills/onfire7777/universal-ai-skills-library/arc-design-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/onfire7777/universal-ai-skills-library/arc-design-review"><img src="https://agentmods.dev/badge/skills/onfire7777/universal-ai-skills-library/arc-design-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 | $0.00090 | $0.00450 |
| Opus 5 | $0.00045 | $0.00225 |
| Sonnet 5 | $0.00018 | $0.00090 |
| Haiku 4.5 | $0.00009 | $0.00045 |
Grade A, and why
arc-design-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 9d 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.
What it actually says
Architect-Refine-Critique Design Review
Overview
A three-phase design review pipeline that produces an Architecture Decision Record.
Phase 1: Architect
- Research the codebase and project conventions
- Identify constraints, requirements, integration points
- Create initial design with component diagrams
- Document structural decisions with reasoning
Phase 2: Refine
- Review the initial design for gaps
- Improve based on best practices and current trends
- Challenge assumptions, verify feasibility
- Produce refined design document
Phase 3: Critique
- Adversarial evaluation of the refined design
- Rate findings by severity (Critical, High, Medium, Low)
- Identify risks, failure modes, scaling concerns
- Propose alternatives where design is weak
Phase 4: Review & ADR
Facilitated discussion with the user:
- Present initial design summary — discuss strengths/weaknesses
- Present refinements — discuss whether they addressed right issues
- Present critique findings one by one — user decides Accept/Reject/Defer
- Synthesize into ADR:
# ADR: [Title]
**Status:** Proposed | **Date:** [today]
## Context: [problem + constraints]
## Decision: [chosen architecture + reasoning]
## Consequences: [positive, negative, mitigations]
## Alternatives Considered: [rejected options + why]
## Process Improvements: [patterns identified during review]
Rules
🚨 Ground every decision in a named principle (SRP, DIP, separation-of-concerns, etc.) 🚨 Discuss ALL phases in order — don't skip. 🚨 Don't decide for the user. Present, discuss, let them choose.
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.
- 9d ago First seen · 50 lines · 90 tokens per session scan A 5e0294e69281
arc-design-review is a skill published in the GitHub repository onfire7777/universal-ai-skills-library (16 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 450 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
jk
Manage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.
harness-init-runner
Initialize a lightweight repo-local Node.js harness (harness/ + .harness/) WITHOUT AIOS dependency. Use ONLY when you need a standalone, portable harness. If AIOS is installed, use aios-long-running-harness instead — it has rex Command hosting, ContextDB integration, and checkpoint recovery.
sudocode
ALWAYS use this skill for ALL sudocode spec and issue operations. Use when user mentions "spec", "issue", "ready", "blocked", "implement", "feature", "plan", or "feedback" with sudocode specs and issues. PROACTIVELY use at start of implementation tasks to check ready issues and understand work context. Operations…
business-defect-audit
A review of whether software follows the intended business rules, even when the code runs, compiles, and passes tests.
parallel-fix
A method for applying a list of mostly independent code fixes at the same time, with one later step to merge and test them.
firefox-cli
Control the user's Firefox from a terminal. Use when your task needs the user's browser or authenticated session, page navigation, tab/window control, screenshots, DOM reads, waits, or page interactions in Firefox. Do not use it as a web search replacement.