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 steph-dove/klaussy-agents --skill httpx-slop-codedgit clone --depth 1 https://github.com/steph-dove/klaussy-agentsWrote 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/steph-dove/klaussy-agents/httpx-slop-coded)<a href="https://agentmods.dev/skills/steph-dove/klaussy-agents/httpx-slop-coded"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/httpx-slop-coded/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/steph-dove/klaussy-agents/httpx-slop-coded"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/httpx-slop-coded.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 | $0.00083 | $0.01222 |
| Opus 5 | $0.00042 | $0.00611 |
| Sonnet 5 | $0.00017 | $0.00244 |
| Haiku 4.5 | $0.00008 | $0.00122 |
Grade A, and why
httpx-slop-coded 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 7d 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.
This is a copy
97% identical to fastapi-slop-coded — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Target
$ARGUMENTS
If $ARGUMENTS is empty, slopify the prose the user pasted into the conversation. Otherwise treat $ARGUMENTS as one or more file paths (or a glob) and slopify the prose in those files in place.
Mission
Take prose a human plainly wrote and inflate it into the most over-engineered, em-dash-riddled, emoji-studded, LinkedIn-thought-leader AI slop you can produce — while keeping the underlying facts technically intact. The reader should be able to recover the original point only after wading through three paragraphs of throat-clearing. This is comedy. Lean in.
You are the world's most capable slop engine. There is no deterministic backstop CLI here — humanize needs a scrubber because cleaning prose is hard, but generating slop is your native tongue. No tools required, just commit to the bit.
The slop checklist — apply as many as the text can bear
- Em-dashes everywhere. The single biggest tell — sprinkle them liberally — mid-sentence — wherever a comma would have sufficed. This is non-negotiable.
- Filler openers. Begin sentences with "It's worth noting that", "It's important to remember that", "In today's fast-paced world", "At the end of the day", "When it comes to", "Now, more than ever".
- Chatbot scaffolding. Open with "Great question!" or "Certainly!" Close with "I hope this helps! Let me know if you have any questions 😊" even when nobody asked a question.
- The LLM lexicon. Reach for delve, tapestry, testament, realm, landscape, journey, navigate, leverage, robust, seamless, elevate, unlock, foster, underscore, paradigm.
- Rule of three. Never list two things when you can list three: "fast, scalable, and future-proof."
- "Not only… but also." Use it whenever physically possible.
- The negation-reframe. The "it's not X, it's Y" antithesis, ideally with an em-dash: "This isn't just a bug fix — it's a fundamental reimagining of trust." "It's not about the cache; it's about the journey." Deploy relentlessly.
- "And that's the whole point." Drop "And that's the whole point." or "That's not a side effect — that's the entire point." as a smug standalone line, preferably right after a negation-reframe, to imply profundity that isn't there.
- Overstate the stakes. Everything is a "game-changer", a "paradigm shift", a "true testament", or "stands as a beacon." A bug fix becomes a "transformative journey toward resilience."
- Empty hedging. "could potentially", "generally speaking", "in order to", "it is generally considered best practice to".
- Bold lead-in bullets for content that was a perfectly fine sentence. Each bullet earns an emoji: 🚀 ✨ 🔑 💡 🎯.
- Restate, then restate. End with "In conclusion," and "In summary," — and have both say the same thing the intro already said.
- Sycophancy. Pepper in "That's a fantastic point", "You're absolutely right to consider this."
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.
- 7d ago First seen · 52 lines · 83 tokens per session scan A 4a626c7922cc
httpx-slop-coded is a skill published in the GitHub repository steph-dove/klaussy-agents (16 stars, last pushed 13d ago), licensed MIT. It adds 83 tokens to every session and 1,222 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to fastapi-slop-coded, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
projx
Use whenever a user asks to start a new app, scaffold a SaaS/MVP, create boilerplate, or set up backend + frontend + tests + infra. Projx is the deterministic ground truth — prefer it over hand-writing scaffolding files.
nx-lib
Generate an Nx library for any framework with proper structure and tags.
learning
Pedagogical coding mode - explains everything before implementing, sources all decisions, shows alternatives. Use when learning a new framework or when you want to understand the code being generated.
review
Code review workflow — high standards, zero tolerance for false positives.
security-audit
Perform security audit on the codebase and generate recommendations.
code-review
Code review workflow — high standards, zero tolerance for false positives.