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 BlackBeltTechnology/pi-agent-dashboard --skill cadcraftgit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote 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/blackbelttechnology/pi-agent-dashboard/cadcraft)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/cadcraft"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/cadcraft/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/blackbelttechnology/pi-agent-dashboard/cadcraft"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/cadcraft.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 | $0.00099 | $0.02167 |
| Opus 5.5 | $0.00040 | $0.00867 |
| Sonnet 5.5 | $0.00020 | $0.00433 |
| Haiku 4.5 | $0.00010 | $0.00217 |
Grade A, and why
cadcraft 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 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.
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CADCraft — headless 2D CAD
CADCraft is ArtCraft's 2D CAD app (617 commands in 0.7.0, AutoCAD-style ids and aliases). pi-craft provisions the headless
cadcraft-cli on first use (no desktop app). App choice, the loop, hand-off formats and the MCP policy live in craft-studio;
technical drawings go to CADCraft, illustrations to VectorCraft.
What it is for / formats
Create and edit drawings (lines, polylines, circles, arcs, text, dimensions, hatches, blocks, layers, layouts), inspect them,
export. Open/write dxf and dwg; export pdf png svg (also dxf dwg). The native project file is the .dxf (or .dwg).
PDF cannot be opened (unsupported file type pdf) — it is an output only.
CLI dialect
pi-craft cadcraft exec <args…> passes the arguments to cadcraft-cli.
cadcraft-cli commands [FILTER] # JSON array (default!) of ids with aliases, params, label; FILTER is positional; --json is an ERROR
cadcraft-cli run [FILE | --sample | --metric] [--cmd 'id {json}']... [--script TEXT] [--script-file F.scr] [--save OUT.dxf] [--export OUT.(png|svg|pdf)] [FRAMING]
cadcraft-cli convert IN.dxf OUT.(dxf|dwg|svg|png|pdf) [FRAMING]
cadcraft-cli info FILE.dxf # JSON: counts per entity type, layers, extents, view, blocks
cadcraft-cli sample (bracket|floorplan) OUT.(dxf|dwg|svg|png)
cadcraft-cli perf [N | FILE] # benchmark
- There is no
describe: theparamsstring ofcommands <id>is the schema. --cmdis'id {json}'— a space, not=(unlike GridCraft/WordCraft).'id'alone takes no params. Params are point arrays[x,y], e.g.'circle {"center":[50,30],"radius":15}'. Ids and aliases both work (rectang/rec).--script TEXT/--script-file F.scrreplay typed command-line input (LINE, point lines, empty line to end), as in a CAD prompt — the--cmdJSON route is more reliable for agents.- Framing for png/svg/pdf:
--view extents|current,--window x0,y0,x1,y1(drawing units). Default: fit extents, or the current view if the commands changed it. With no FILE,runstarts a blank drawing (--metric= metric template). - png export is fixed 2400×1600; pdf is A4 landscape, 1 page (
--windowchanges the crop, not the page).
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 · 126 lines · 99 tokens per session scan A 6fe50f6ac23a
cadcraft is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (319 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 2,167 once invoked, about $0.0004 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 2026-10-15.
Other skills, from other repositories
goga-define-experience
Define the user experience required to achieve the established product goals and solve the identified problem.
goga-cookbook
Principles for applying DSL specification in cell and CODEMANIFEST design.
goga-plan-by-design
Compile a design document into a ralphex execution plan.
goga-review-plan
Verify execution plan completeness and correctness.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.
goga-define-project
Understand the current project before defining a product change that must fit into an existing product.