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 urmzd/dotfiles --skill review-designgit clone --depth 1 https://github.com/urmzd/dotfilesWrote 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/urmzd/dotfiles/review-design)<a href="https://agentmods.dev/skills/urmzd/dotfiles/review-design"><img src="https://agentmods.dev/badge/skills/urmzd/dotfiles/review-design/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/urmzd/dotfiles/review-design"><img src="https://agentmods.dev/badge/skills/urmzd/dotfiles/review-design.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 | $0.00102 | $0.01782 |
| Opus 5.5 | $0.00041 | $0.00713 |
| Sonnet 5.5 | $0.00020 | $0.00356 |
| Haiku 4.5 | $0.00010 | $0.00178 |
Grade A, and why
review-design 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pragmatic Programming
Layering: Principles layer above
assess-quality(foundational framework) and are operationalized bywrite-code(tool/pattern picks). Use this skill when reasoning about why a design tradeoff matters; useassess-qualityfor the underlying quality framework; usewrite-codefor concrete picks.
Principles from The Pragmatic Programmer (Hunt & Thomas) distilled into actionable rules for everyday development.
Core Philosophy
- Care about your craft why spend your life developing software unless you care about doing it well?
- Think critically question assumptions, challenge "because we've always done it that way"
- Be a catalyst for change show people a future they can rally around (stone soup)
- Remember the big picture don't get so absorbed in details that you forget the system as a whole (boiling frog)
- Good enough software know when to stop; perfect is the enemy of shipped
ETC: Easy to Change
The fundamental design principle. Every decision should make future change easier.
- When choosing between approaches, pick the one that's easier to change later
- If you can't decide which path is more changeable, fall back on: make it replaceable
- Decoupled code is easier to change; single-responsibility code is easier to change; well-named code is easier to change. ETC is the why behind all of them
DRY: Don't Repeat Yourself
Every piece of knowledge must have a single, unambiguous, authoritative representation within a system.
| Violation | Fix |
|---|---|
| Copy-pasted logic | Extract shared function/module |
| Knowledge in code AND comments | Let code be the authority; remove redundant comments |
| Same validation in client and server | Single schema, generate both |
| Repeated config across environments | Template or derive from one source |
| Data structure duplicated across types | Single source type, derive others |
- DRY applies to knowledge, not text. Two functions with identical code but representing different knowledge are not DRY violations
- Watch for DRY violations across: code, documentation, data schemas, API specs, build config
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 · 173 lines · 102 tokens per session scan A f967daa43a2a
review-design is a skill published in the GitHub repository urmzd/dotfiles (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 102 tokens to every session and 1,782 once invoked, about $0.0004 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
pr-review
Intelligent PR code review with dynamic agent allocation based on change types. Analyzes PR changes and generates targeted review tasks.
analyze-pr
Analyze a GitHub/GitLab Pull Request by fetching its diff, reading its web description, and generating a comprehensive document. Use when the user provides a PR link and wants to understand what changes the PR introduces, or asks to review/analyze/summarize a pull request.
review-code
Standalone code review for any scope — PR number, branch, file paths, or current changes. Synthesizes intent, runs 12 parallel specialized agents, and presents actionable findings with a verdict. A dependency update (Dependabot, Renovate, any lockfile change) gets a check of each release it adopts instead. For PR…
review-converge
Autonomously review and fix the current branch or specified scope in iterative rounds until clean, leaving all changes in the working tree. Escalates only genuine design decisions. Ends with a transparent report of every round, every fix, and anything it couldn't resolve.
review-pr-comments-converge
Fetch PR review comments, validate each against the actual code, auto-fix obvious issues, and escalate genuine design decisions. Leaves all changes in the working tree. Use when you want to action reviewer feedback autonomously.
review-prs
Fetch and present a prioritized summary of all PRs awaiting the current user's review across the relevant projects and provide an interactive workflow helping the user phrase and post inline review comments and overall review decisions.