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 agentmods add commands/ronmkr/promptbook/maker-setupgit clone --depth 1 https://github.com/ronmkr/PromptBookWrote 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/commands/ronmkr/promptbook/maker-setup)<a href="https://agentmods.dev/commands/ronmkr/promptbook/maker-setup"><img src="https://agentmods.dev/badge/commands/ronmkr/promptbook/maker-setup.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.00380 |
| Opus 5 | $0.00015 | $0.00190 |
| Sonnet 5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
maker-setup scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- If `git` is **not** available: don't install it. Download the GitHub tarball instead — `curl` and `tar` ship with macOS, Linux, and Windows 10+ out of the box: What it actually says
The user has a Cardputer-Adv from gemini.com/cwc-makers plugged in over USB-C.
- Get https://github.com/moremas/build-with-gemini into a
build-with-gemini/directory under cwd:- If
gitis available:git clone(orgit pullif it already exists). - If
gitis not available: don't install it. Download the GitHub tarball instead —curlandtarship with macOS, Linux, and Windows 10+ out of the box:- macOS / Linux:
curl -L https://github.com/moremas/build-with-gemini/archive/refs/heads/main.tar.gz | tar xz && mv build-with-gemini-main build-with-gemini - Windows (PowerShell):
curl.exe -L -o bwc.zip https://github.com/moremas/build-with-gemini/archive/refs/heads/main.zip; tar -xf bwc.zip; Rename-Item build-with-gemini-main build-with-gemini
- macOS / Linux:
- Re-running
/maker-setuplater just re-downloads (~500KB) — no update mechanism needed.
- If
- Invoke the
m5-onboardskill and follow it to runonboard/scripts/onboard.py --apps buddyfrom insidebuild-with-gemini/, surfacing the download-mode button prompt to the user. - When done, tell the user how to launch Gemini Buddy and ask what they want to build next (see the
cardputer-buddyskill for iterating).
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.
- 3d ago First seen · 16 lines · 31 tokens per session scan A f12866e946ee
maker-setup is a command published in the GitHub repository ronmkr/PromptBook (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 380 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
ros-robotics
作为一名资深 ROS 机器人开发工程师来处理这次请求。.
spec-design
Create comprehensive technical design for a specification.
observe
部屋を能動的に観察する。3つの基本ブロックを自由に選びながらループし、受動的なスナップショットではなく発見のある観察を行う。.
model
Check if an AI model fits on your GPU before downloading.
eol-report
EOL/EOS risk report — devices, OS versions, and firmware approaching or past end-of-life/end-of-support, prioritized by criticality.
gum-search
BM25 search the embedded catalog (TTY table, pipe JSON).