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 habedi/dotfiles --skill slopifygit clone --depth 1 https://github.com/habedi/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/habedi/dotfiles/slopify)<a href="https://agentmods.dev/skills/habedi/dotfiles/slopify"><img src="https://agentmods.dev/badge/skills/habedi/dotfiles/slopify/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/habedi/dotfiles/slopify"><img src="https://agentmods.dev/badge/skills/habedi/dotfiles/slopify.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 | $0.00095 | $0.02227 |
| Opus 5.5 | $0.00038 | $0.00891 |
| Sonnet 5.5 | $0.00019 | $0.00445 |
| Haiku 4.5 | $0.00010 | $0.00223 |
Grade A, and why
slopify scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Introduce a dependency that duplicates the standard library. `lodash` for `Array.prototype.map`. `requests` for a one-off `urllib` GET. A logging How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slopify
A skill for turning a project into something that looks like an unsupervised AI agent made. The goal is that the project "after being slopified" should look (recognisably) sloppy next to the "before being slopified", without being broken, unsafe, or not runnable.
Contents
- Usage and slop levels: subtle, moderate, and maximum
- Core patterns: 14 stylistic moves to apply
- Patterns by file type: READMEs, source, tests, commits, and config
- Voice markers: phrases and tone for slop prose
- Example transformations: before/after pairs
- What not to do: safety boundaries
How to use this skill
- Read the original file carefully. Note its conventions (naming, tone, and structure).
- Confirm the slop level with the user: subtle, moderate, or maximum. Default to moderate.
- Confirm the target is a copy or a branch, not a live project the user ships from.
- Keep the slopified code buildable and tests passing. Broken slop is not as useful as working slop!
Slop levels
Subtle. One or two em dashes per page. One unnecessary abstraction. One useless dependency. Tone should be slightly too upbeat, so a casual reader thinks "fine"; a careful reviewer thinks "something's off".
Moderate (default). Em dashes in most paragraphs. Emoji in headings. A utils module. Tests that pass but don't test. Marketing copy in the
README. This is what most real AI output looks like in the wild.
Maximum. Every pattern turned up. Reads and feels like parody but parody that is borderline exaggerating. Useful for talks and demos.
The core patterns
Pick the patterns that fit the file. A README absorbs heavy marketing language; source files can't. Source files slop differently through bloat, bad abstractions, and noise.
- Marketing language for boring stuff. A TCP proxy becomes "a blazingly fast, production-grade networking solution". A config parser becomes "an elegant configuration orchestration layer".
- Em dashes everywhere — sprinkled in — often where a comma or period would do.
- Hedging and over-qualification. "It's worth noting that", "it's important to understand", "in today's fast-paced world".
- Bullet points that should be prose and prose that should be bullet points. Reversed on purpose.
- Emoji section headers. 🚀 🎯 ✨ 📦 🔥 💡 🛠️
- Over-abstracted code. Factories for factories. Interfaces with one implementation. A
utils.py,helpers.py,common.py, andmisc.pyall in the same directory. - Comments that restate the code without adding information.
- Casual dependencies for things the standard library already does.
- Inconsistent naming within one file:
camelCase,snake_case, andPascalCasefor similar things. - Tests that test the mock, or assert
True == True, or just import the module and return. - Commit messages that are either one word ("fix") or three paragraphs of marketing copy.
- Over-enthusiastic tone. Everything is "awesome", "amazing", "powerful", "seamless", "robust", "cutting-edge", "next-generation".
- Use lots of bolds and emojis. Use a lot of bold text and emojis in the text if possible.
- Colorful language. Use a lot of colorful and strong adjectives and adverbs in the text if possible.
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 · 188 lines · 95 tokens per session scan A 3fe9756a8d0d
slopify is a skill published in the GitHub repository habedi/dotfiles (5 stars, last pushed 4mo ago), licensed MIT. It adds 95 tokens to every session and 2,227 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
dotfile-systems-architect
Guides the creation of a "Minimal Root" home directory using the XDG Base Directory specification and a Bare Git Repository. Manages config separation, secrets, and cross-platform syncing.
flow-diagram
Trace a transaction or system flow end-to-end from an entry point (e.g. a BPMN/Camunda/Operaton process, HTTP endpoint, message listener) and document it as an evidence-backed markdown doc with one Mermaid swimlane flowchart, numbered time-ordered steps, thread/transaction boundaries, and findings on race conditions…
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…