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 | $0.00444 |
| Opus 5.5 | $0.00005 | $0.00178 |
| Sonnet 5.5 | $0.00003 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00044 |
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 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Choose the missing surface
Use current harness docs and examples, not remembered APIs. Start from who initiates the workflow and what the harness or an existing CLI already does. Prefer a direct command or thin wrapper. An extension must need hooks, state, UI, or tool registration. Resolve an ambiguous product choice with the user, but implement an already specified or delegated shape without another approval round.
- Users operate UI and slash commands. Agents use tools or discoverable CLIs. Do not mirror the two surfaces by default.
- Keep rare user-invoked work out of permanent agent tools. Give the agent only choices it must make, not host policy or backend machinery.
- Reuse the setup's navigation and settings patterns. Put related actions and persistent settings in one skimmable management surface. Configuration files are storage, not the interface.
- Keep machinery proportional to the actual risks. Remove speculative modes, compatibility layers, and configuration. Agent results need useful state or a next action, not the surrounding workflow.
Load an applicable tool-design skill before changing an agent-facing tool. The README explains outcome, installation, first action, and material boundaries. Ordinary settings and actions belong in the product.
Validate the right surface
Choose checks for concrete risks in the change, not a per-edit checklist. Routine wording edits do not require a behavioral study or an integration harness.
- Before changing the live setup, test runtime changes locally. Consult current harness controls for isolation.
- For tool-surface or prompt-assembly changes, inspect the affected emitted contracts and measure their token cost with existing tooling. Do not turn copy edits into whole-task performance comparisons.
- When agent behavior needs evaluation, load an applicable instruction-calibration skill. Test natural use and the nearest non-use case with model, task, context, and harness version held fixed. Close finished test panes.
- For activation, lifecycle, or extension-interoperability changes, check the affected workflow in the complete extension setup. Leave live activation to the user's existing authorization. Human UX acceptance still belongs to the user.
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 Changed · -32 lines ebf6bb8659a8
- 2mo 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 (413 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 444 once invoked, about $0.0001 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 2026-08-30.
extension-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| extension-designIgorWarzocha/howaboua-pi-stuff | Skill | 413 | yesterday | MIT | A | 13 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |