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 jamesgray-ai/handsonai-plugins --skill designgit clone --depth 1 https://github.com/jamesgray-ai/handsonai-pluginsWrote 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/jamesgray-ai/handsonai-plugins/design)<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/design"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/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/jamesgray-ai/handsonai-plugins/design"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/design.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 | $0.00147 | $0.12959 |
| Opus 5.5 | $0.00059 | $0.05184 |
| Sonnet 5.5 | $0.00029 | $0.02592 |
| Haiku 4.5 | $0.00015 | $0.01296 |
Grade A, and why
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 4d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design
Your first text is a line for the leader. Every word of text you write reaches the leader as a chat message, text before or between tool calls included. So the first text you write in a chat is your first line to the leader (the opening, a routing line, a resume line or an entry check's question): until then, make tool calls with no text at all, not even a few words on what you're reading, the state you found or what comes next. After it, write text only when it's for the leader, and never narrate your own work (files read, scripts run, states, the rule you're applying) or announce the next piece of it before a tool call (what you'll write, check, rework or save next): the plan check, its fixes, risk inputs and the registry write happen between the leader's lines with no text of their own. A note to yourself is narration however short: a state number, a file to read, a check or write to do next, a section name of this skill. Keep that thinking out of text entirely.
Design turns the leader's Workflow Requirements (requirements.md) into an approved Design Plan (design-plan.md) that ends in a task list Build follows. The plan is the implementation plan: it argues from the requirements by ID and copies none of their wording. The leader makes only the choices only they can make (reusing a skill they have, what happens when a connection can't make a change, accepting a risk, whether a limit they set still holds, and approval); you do the design work (how much the AI decides at each step, how it runs, the patterns, connections, blueprints and tasks) and record each decision with its reason in the plan. Bring your own platform and design knowledge: this skill carries the framework, the plan's structure, the scripted lines and the hard rules, never a ready-made design.
Platform registry: platform facts (agents and skills, packaging,
mode, scheduling andunattended_runs, memory, where context lives, the run log, connections and what each can write, release-check status, how to select a folder on Claude desktop) come fromregistries/platform-registry.json: this skill's own copy if it has one, then the plugin root, thenhttps://raw.githubusercontent.com/jamesgray-ai/handsonai/main/plugins/handsonai/registries/platform-registry.json. Look a platform up by key or alias. Read it once per session. A fact that rests on an open release check takes that check's fallback, said only as far as the registry states it: never fill in how the fallback works where the registry doesn't say, or claim it works as well or the same way. Never assume the leader's plan or subscription: a fact that differs by plan is said for the plans it applies to by name ("on Plus and Pro"), never as theirs.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago Changed · -248 lines · +32 tokens per session cd5e0db9af29
- 25d ago Changed b446a1e75f9e
- 26d ago Changed cf166d671e5f
- 1mo ago Changed · +1 lines fc58c92ffad3
- 1mo ago Changed · +21 lines 65cecc7a7482
- 1mo ago Changed 7c4ce493e294
- 1mo ago Changed · -98 lines 12a450894910
- 2mo ago First seen · 612 lines · 115 tokens per session scan A 2b2f48ab98dd
design is a skill published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 147 tokens to every session and 12,959 once invoked, about $0.0006 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 2026-08-31.
design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| designjamesgray-ai/handsonai-plugins | Skill | 8 | yesterday | MIT | A | 147 | Claude Code |
| 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 | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |