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 IgorWarzocha/howaboua-pi-stuff --skill extension-designgit clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuffWrote 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/igorwarzocha/howaboua-pi-stuff/extension-design)<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/extension-design"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/extension-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/igorwarzocha/howaboua-pi-stuff/extension-design"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/extension-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00013 | $0.00940 |
| Opus 5 | $0.00006 | $0.00470 |
| Sonnet 5 | $0.00003 | $0.00188 |
| Haiku 4.5 | $0.00001 | $0.00094 |
Grade A, and why
extension-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 9d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Choose the surface before coding
Start from the experience the user wants, not from extension machinery. Before implementation, identify:
- who initiates the workflow
- how often it occurs
- what the harness or an existing CLI already provides
- which interface the workflow actually needs
Choose between direct CLI use, a script, skill, user-invoked slash command, human UI, agent tool, or extension integration. Confirm that shape with the user before writing code.
Prefer the smallest missing piece. If a CLI already owns the capability but is awkward to use from the harness, wrap it thinly rather than rebuilding it. Custom extension behaviour is earned by integration needs such as UI, state, hooks, events, or tool registration.
Do not register an agent tool merely because an extension can. A permanent tool must earn its model cost through repeated natural use or a capability the agent cannot otherwise reach. For rare or explicitly requested workflows, prefer a user-invoked command, script, or CLI, with a skill only when the agent needs invocation guidance.
Fit the real harness
Inspect the user's setup and conventions before designing around an abstract ideal. Reuse its existing navigation, settings, command, and tool patterns. Add engineering machinery only for risks and requirements present in this workflow. Do not turn a personal convenience into an enterprise subsystem because testing, permissions, retries, compatibility layers, or configurability sound generically respectable.
Treat the human interface and agent toolkit as separate products. Either may exist without the other, and they should not be mirrored by default.
- Users operate interfaces and slash commands. A prompt-template command is still user-invoked, not an agent capability.
- Agents use tools or discoverable CLIs. Give them only decisions they genuinely make, and keep deterministic policy and implementation choices in the host.
- If settings, persistent state, or several user actions exist, prefer one skimmable management surface. Configuration files are storage, not the ordinary interface.
- Where both audiences need the same underlying operation, share its implementation while giving each audience the vocabulary and result it needs.
- Agent-facing results should say what happened and provide the state, evidence, path, handle, recovery, or exact continuation naturally needed next. Do not enlarge a tool to swallow the surrounding workflow.
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.
- 9d ago First seen · 58 lines · 13 tokens per session scan A 825b07d661db
extension-design is a skill published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (358 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 940 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…