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/thevibeworks/claude-code-docs/maker-setupgit clone --depth 1 https://github.com/thevibeworks/claude-code-docsWrote 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/thevibeworks/claude-code-docs/maker-setup)<a href="https://agentmods.dev/commands/thevibeworks/claude-code-docs/maker-setup"><img src="https://agentmods.dev/badge/commands/thevibeworks/claude-code-docs/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 | $0.00029 | $0.00378 |
| Opus 5 | $0.00015 | $0.00189 |
| 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 yesterday.
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: This is a copy
100% identical to maker-setup — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
The user has a Cardputer-Adv from claude.com/cwc-makers plugged in over USB-C.
- Get https://github.com/moremas/build-with-claude into a
build-with-claude/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-claude/archive/refs/heads/main.tar.gz | tar xz && mv build-with-claude-main build-with-claude - Windows (PowerShell):
curl.exe -L -o bwc.zip https://github.com/moremas/build-with-claude/archive/refs/heads/main.zip; tar -xf bwc.zip; Rename-Item build-with-claude-main build-with-claude
- 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-claude/, surfacing the download-mode button prompt to the user. - When done, tell the user how to launch Claude 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.
- yesterday First seen · 16 lines · 29 tokens per session scan A 326e604a0501
maker-setup is a command published in the GitHub repository thevibeworks/claude-code-docs (39 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 378 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to maker-setup, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
reconcile
Check developer guides for documentation drift against recent code changes.
audit
Re-audit accepted ADRs against the codebase — verify each still holds, then amend, supersede, or deprecate the ones that don't.
review
Review proposed ADRs for lifecycle progression — accept implemented decisions, deprecate stale ones, archive trivial ones.
from-spec
Extract Architecture Decision Records from a completed spec.
curate
Curate research files — inventory by type, identify stale/superseded candidates, update frontmatter status.
create
Create a new Architecture Decision Record.