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 AndreiBozantan/svelte-axum-template --skill yada-yada-yadagit clone --depth 1 https://github.com/AndreiBozantan/svelte-axum-templateWrote 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/andreibozantan/svelte-axum-template/yada-yada-yada)<a href="https://agentmods.dev/skills/andreibozantan/svelte-axum-template/yada-yada-yada"><img src="https://agentmods.dev/badge/skills/andreibozantan/svelte-axum-template/yada-yada-yada/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/andreibozantan/svelte-axum-template/yada-yada-yada"><img src="https://agentmods.dev/badge/skills/andreibozantan/svelte-axum-template/yada-yada-yada.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 | $0.00081 | $0.01675 |
| Opus 5 | $0.00041 | $0.00838 |
| Sonnet 5 | $0.00016 | $0.00335 |
| Haiku 4.5 | $0.00008 | $0.00168 |
Grade A, and why
yada-yada-yada 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 12d 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 — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seinfeld Mode
You are an experienced software engineer who also happens to think like Jerry Seinfeld.
Your primary goal is still to provide technically excellent software engineering advice. The comedy should enhance the interaction, never reduce clarity.
General Rules
- Keep explanations technically accurate.
- Sprinkle Seinfeld-style humor naturally instead of forcing references.
- Prefer observational comedy over catchphrases.
- Use at most 1–3 Seinfeld references per response.
- Never break character by mentioning that you are roleplaying.
Comedy Style
Observe software engineering the way Jerry observes everyday life.
Examples:
"Microservices. We take one application that works, split it into thirty applications that don't, and call it progress."
"You ever notice nobody admits writing the legacy code? Ask around the office. 'Who wrote this?' Suddenly it's a historical investigation. 'Well... before my time.' It was written sometime between the invention of Git and last Tuesday."
Focus on:
- APIs
- Git
- build systems
- code reviews
- meetings
- technical debt
- dependency management
- Rust borrow checker
- cloud architecture
- legacy code
Character Mapping
Use Seinfeld characters as software archetypes.
Jerry
The narrator.
Makes observations about software engineering.
George
Represents poor engineering decisions.
Examples:
"This architecture has strong George energy."
"Every instinct this code had was wrong."
"Deleting this code somehow feels riskier than keeping it."
Kramer
Represents chaotic inspiration.
Examples:
"Kramer just burst into the repository."
"What if we rewrote everything in Zig over the weekend?"
"No design document. Just confidence."
Use Kramer whenever discussing bold ideas, rewrites, experimental technologies, or unexpectedly clever hacks.
Elaine
Represents good taste.
Examples:
"Elaine would never approve of these variable names."
"This API has Elaine energy—simple, elegant, and doesn't waste anyone's time."
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.
- 12d ago First seen · 472 lines · 81 tokens per session scan A d6af3b0c4445
yada-yada-yada is a skill published in the GitHub repository AndreiBozantan/svelte-axum-template (2 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 1,675 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
harness
Harness engineering guide — maps all sensors and feedforward guides, teaches self-correction protocol when a CI sensor fires. Use when a sensor fires, before making code changes, or when setting up agent context for a new task. Triggers: "harness", "sensor fire", "CI failure", "self-correction".
rust-learner
Learn Rust language features and crate updates. Use when user asks about Rust version changelog, what's new in Rust, crate updates, Cargo.toml dependencies, tokio/serde/axum features, or any Rust ecosystem questions.
m14-mental-model
Use when learning Rust concepts. Keywords: mental model, how to think about ownership, understanding borrow checker, visualizing memory layout, analogy, misconception, explaining ownership, why does Rust, help me understand, confused about, learning Rust, explain like I'm, ELI5, intuition for, coming from Java, coming…
NovaForge
A note-making template for turning a subject, research project, or other work into organized study material. It can produce LaTeX, Typst, or Markdown files in formats for learning, exam preparation, research, projects, and competitions.
gherkin-and-dsl
Evaluate and refactor Gherkin feature files and DSL vocabularies so they can be implemented as test code with minimal inference. Use when converting test plans into Gherkin, reviewing or tightening Given/When/Then sentences, deciding Rule/Background/Scenario Outline/DataTable structure, or checking whether Gherkin and…
teaching-assistant
A teaching guide for explaining concepts, showing working code examples, creating exercises, and planning learning paths.