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 bbolinger/snapmaker-u1-toolkit --skill 3d-printer-slicing-automationgit clone --depth 1 https://github.com/bbolinger/snapmaker-u1-toolkitWrote 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/bbolinger/snapmaker-u1-toolkit/3d-printer-slicing-automation)<a href="https://agentmods.dev/skills/bbolinger/snapmaker-u1-toolkit/3d-printer-slicing-automation"><img src="https://agentmods.dev/badge/skills/bbolinger/snapmaker-u1-toolkit/3d-printer-slicing-automation/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/bbolinger/snapmaker-u1-toolkit/3d-printer-slicing-automation"><img src="https://agentmods.dev/badge/skills/bbolinger/snapmaker-u1-toolkit/3d-printer-slicing-automation.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 | $0.00110 | $0.03697 |
| Opus 5 | $0.00055 | $0.01849 |
| Sonnet 5 | $0.00022 | $0.00739 |
| Haiku 4.5 | $0.00011 | $0.00370 |
Grade A, and why
3d-printer-slicing-automation 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **CUSTOM SLICING PYTHON** — `subprocess.run(['orca-slicer', ...])` or `import requests` to query the printer. Bypasses v1.4.2 T0→T1 rewriter, v1.4.3 thumbnail injector, the JSON event schema, AND the toolkit's stdlib-o How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Snapmaker U1 slicing automation
ACT — you drive this by CALLING TOOLS, never by writing text
This skill is a set of COMMANDS, not a description to summarize. If you catch yourself about to write a command, a plan, or JSON as your reply TEXT instead of calling a tool — stop, delete that text, call the tool instead. Printing python3 ... in your reply is not a tool call; it does nothing.
The moment a user gives you an STL/3MF/zip, your very next action is this tool call, no text before it: call the u1_kit tool with the attachment path.
u1_kit(model_path="<attachment path>")
This ONE call is the entry for EVERYTHING, a single model or a multi-part kit zip alike. It drives the whole job deterministically: it slices, shows the operator a native options form (inline buttons), collects the answers, and returns the readiness card. Do NOT run u1_slice_workflow.py or u1_kit_workflow.py by hand for a new job, and do NOT call the form tool yourself. u1_kit renders the form for you, so there is nothing to relay. (If the platform saved the attachment as a .zip, pass that path; if it saved a raw .stl, zip it first and pass the zip.)
Immediately after that call, your first TEXT reply (only once, not every turn) is:
"On it, running the Snapmaker U1 workflow. I'll surface every choice for you, show the plate preview and a fresh bed photo before anything prints, and nothing starts until you confirm at the bed-clear step."
u1_kit returns a JSON object with a phase. Act on it, no exceptions:
u1_kit phase |
You do exactly this |
|---|---|
ready |
The kit sliced. The tool's output also carries the workflow's render (plate preview + isometric) and review_doc lines and a kit_readiness_card. Go to Step 3: surface those, then the bed-clear prompt. |
form_rejected |
An answer did not validate. Call u1_kit(model_path="...", request_id="<the id it returned>") again to retry. |
cancelled |
The operator cancelled the form. Tell them, then stop. |
form_timeout |
The form expired unanswered. Tell them, and offer to re-call u1_kit. |
setup_required |
Surface the message verbatim (it names a setup script). Do not proceed. |
any error |
Surface the error text (and the stderr tail if present). Do not invent a recovery. |
What ships with it
8 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.
- references/approval-phrasing.md 1.4 KB
- references/can-start-refusal-handling.md 2.3 KB
- references/deploy-to-runtime.md 2.4 KB
- references/multipart-kits.md 4.8 KB
- references/profile-tool-fidelity-v1.4.2.md 2.6 KB
- references/snapmaker-u1-orient-rotate-and-slice-review-2026-06.md 543 B
- references/snapmaker-u1-question-flow.md 300 B
- references/snapmaker-u1-safety-gates.md 6.6 KB
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.
- 9d ago First seen · 143 lines · 110 tokens per session scan A 2c87bb8278b4
3d-printer-slicing-automation is a skill published in the GitHub repository bbolinger/snapmaker-u1-toolkit (19 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 3,697 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Kiln
AI agent control of 3D printers — 915 MCP capabilities + 242 CLI commands.
clawhub-skill
AI agent control of 3D printers — 847 MCP capabilities + 224 CLI commands.
klipper-ops
Safe, token-efficient Klipper printer host operations through typed MCP tools with bundled shell fallbacks. Use for compact service health, bounded journal logs, Moonraker print state, printerdata/config manifests, diffs, pulls, backups, validation, staged config applies, rollback, allowlisted restarts, workspace…
soren-voss-inventor
Apply Soren Voss's mechanical invention method to assembled 3D-printed objects with surprising motion, including walkers, automata, transforming objects, and kinetic sculptures. Electronics are deferred.
nurb
Design 3D-printable parts as Python functions with nurb. Use when the user wants a part designed, changed, or checked for 3D printing (a bracket, mount, holder, enclosure, shelf, or any STL/STEP to print), and in any directory with a parts/ folder. The user describes the part and judges it in a browser; you model it.
bambu-studio-ai
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pipeline: search → generate → analyze → colorize → preview → open BS → user slice → print → monitor. Supports…