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 assess-qualitygit 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/assess-quality)<a href="https://agentmods.dev/skills/urmzd/dotfiles/assess-quality"><img src="https://agentmods.dev/badge/skills/urmzd/dotfiles/assess-quality/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/assess-quality"><img src="https://agentmods.dev/badge/skills/urmzd/dotfiles/assess-quality.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 | $0.00120 | $0.02595 |
| Opus 5.5 | $0.00048 | $0.01038 |
| Sonnet 5.5 | $0.00024 | $0.00519 |
| Haiku 4.5 | $0.00012 | $0.00260 |
Grade A, and why
assess-quality 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality
Layering: Foundational why;
review-designandwrite-codebuild on this. Use this skill when defining the quality bar or arbitrating between principles (review-design) and operational picks (write-code).
The Workshop Principle
Different writers, same pragma.
Every tool, library, and script should feel like it came from the same workshop. The way Microsoft tools feel consistent, the way Google tools share a coherent design language; our code should have that same unity. A developer who has used one of our CLIs should feel at home in any other. An AI agent that has parsed one project's JSON output should know what to expect from the next.
This is not about aesthetics. Consistency reduces cognitive load for both audiences:
- Developers spend less time learning conventions and more time solving problems
- AI agents parse structured output, consume skills-as-docs, and navigate codebases via AGENTS.md
Every convention in our skill system (JSON output, color semantics, commit style, file organization) traces back to this principle. If a decision doesn't serve consistency or intentionality, question it.
The Dual Audience
We build for two consumers simultaneously:
Developers read source code, run CLIs, review PRs, and onboard to projects. They need readable code, obvious entry points, and one-command workflows.
AI agents parse JSON output, consume SKILL.md files as executable context, discover projects via llms.txt, and navigate architecture via AGENTS.md. They need structured interfaces, predictable patterns, and machine-readable output.
Every interface decision must answer both: Can a human understand this? Can an agent parse this?
This is why:
- CLIs emit JSON agents chain it, skills consume it, content persists
docs/organizes project documentation by purpose (guides/, rfcs/, plans/, runbooks/). Skills provide executable agent context alongside- llms.txt exists projects become AI-discoverable
- AGENTS.md mirrors README agents get the same onboarding humans do
- Commit messages follow Angular parseable by sr for automated releases
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 · 208 lines · 120 tokens per session scan A d038b3d6df28
assess-quality is a skill published in the GitHub repository urmzd/dotfiles (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 120 tokens to every session and 2,595 once invoked, about $0.0005 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 11 parallel specialized agents, and presents actionable findings with a verdict. For PR scope, optionally posts the review to GitHub with inline comments.
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-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.
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.