Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/skyciv/skyciv-ai-skillsnpx agentmods add skills/skyciv/skyciv-ai-skills/baseplateWrote 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/skyciv/skyciv-ai-skills/baseplate)<a href="https://agentmods.dev/skills/skyciv/skyciv-ai-skills/baseplate"><img src="https://agentmods.dev/badge/skills/skyciv/skyciv-ai-skills/baseplate/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/skyciv/skyciv-ai-skills/baseplate"><img src="https://agentmods.dev/badge/skills/skyciv/skyciv-ai-skills/baseplate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00253 | $0.06072 |
| Opus 5.5 | $0.00101 | $0.02429 |
| Sonnet 5.5 | $0.00051 | $0.01214 |
| Haiku 4.5 | $0.00025 | $0.00607 |
Grade A, and why
baseplate 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 14d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Base Plate Design
Design and check a steel column base plate connection — base plate, anchor bolts, welds and the
concrete below — with the SkyCiv standalone.baseplate API.
Prerequisite: open the session with
standalone.baseplate.start, notS3D.session.start(verified: a check afterS3D.session.startreturns "Session has not been started. Please call standalone.baseplate.start first."). Auth,optionsand the{ auth, options, functions }envelope are inskyciv-api-v3.
Only concentric column / plate / foundation layouts with symmetric anchors are supported.
Workflow
- Choose
design_codeand load its reference file — it holds every accepted material, grade, diameter, electrode and thefactorsblock for that code:American·Australian·Canadian·Europe. - Start from that code's
sample-api/<country>/input.js(see Worked examples) and change only what you need. Every key must be present, even unused ones. - Send
standalone.baseplate.startthenstandalone.baseplate.checkin one request.design_objis theargumentsobject — not nested under another key. - Check
response.status. On1, readerrors/warnings/conflicts(below) and fix the input. - Scan every check for its
ratio(see Reading the response).
"functions": [
{ "function": "standalone.baseplate.start", "arguments": { "keep_open": true } },
{ "function": "standalone.baseplate.check", "arguments": { "design_code": "American", "...": "..." } }
]
Several checks can follow one start in a request (verified; top-level response is the last).
Each check takes about 11–20 s and uses one API credit.
Gotchas
- Invalid strings are silently replaced, not rejected. An unknown material, concrete grade or
anchor diameter returns
status: 0with results computed on a default value (verified for column, base plate, anchor and concrete grades, and Canadian diameters). Copy values exactly from the reference file, and confirm the relevant capacity moved when you change one. - Canadian anchor diameters are imperial sizes in mm (
12.7,15.9,19.1,22.2…). The12, 16, 20…list in the live docs is silently ignored — seecanadian.md. - A failing
detailingcheck hangs the call instead of erroring. Verified withembed_plate(embedded plate side < 4 × anchor diameter): noconflictsare returned — the call runs until the server timeout (~45 s) and returns "standalone.baseplate.check timed out".options.timeoutdoes not extend it. Treat any timeout as an input problem: check the detailing rules below against your geometry before retrying. Mymust be"0". It is reserved for future weak-axis support; any non-zero value ("1","10") hangs the call until timeout.- A
fixedbase needs a non-zeroMzin every load case. Otherwisestatus: 1with the conflict "configured as a fixed support, but the load combination does not include a moment". Axial-only or axial + shear cases go on apinnedbase. - A wrong section name fails fast with an unhelpful message — "could not be completed for an
unknown reason" in ~5 s.
steel-column-databaseis the third level of the section library path andsteel-column-profilethe fourth (e.g.American › AISC › Pipes › Pipe6STD→"Pipes","Pipe6STD"). Resolve both withsection-selector. status: 0does not mean the design passes — a run returned a breakoutratio: 1.248withstatus: 0. Derive pass/fail from the ratios.capacity: 0withratio: 0means "not evaluated", not a pass with infinite margin — e.g.Weld Capacityon an axial-only pinned base,Side-Face Blowout (Y-Direction)when no anchor is near that edge. Report these as N/A.Concrete Bearing Capacitysits atratio: 1for American/Canadian fixed bases under large moment. Ratio 1 = demand equals capacity (limit reached). This method takes bearing stress at its limit and solves for the bearing length, so the ratio stayed1.000when the plate grew 400 → 500 mm and the footing 450 → 900 mm. Report it as at-limit, but size the connection on the other checks — enlarging the plate won't move it. Small eccentricity (Nx = 200,Mz = 2) gave0.102.- Load values are strings (
"Mz": "10") in every sample; keep them strings. - Report URLs are temporary (
solver.skyciv.com/temp/...). - Strip
screenshotbefore logging a failure —status: 1responses carry a 60–200 KB base64 PNG of the calculator UI. Decode it only when diagnosing.
What ships with it
12 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/american.md 3.7 KB
- references/australian.md 3.3 KB
- references/canadian.md 3.4 KB
- references/europe.md 4.5 KB
- sample-api/america/input.js 5.0 KB runs code
- sample-api/america/response.json 7.3 KB
- sample-api/australia/input.js 5.5 KB runs code
- sample-api/australia/response.json 3.3 KB
- sample-api/canada/input.js 5.8 KB runs code
- sample-api/canada/response.json 7.3 KB
- sample-api/europe/input.js 6.1 KB runs code
- sample-api/europe/response.json 3.7 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.
- 14d ago Changed · -194 lines · +253 tokens per session b35d246167b0
- 2mo ago First seen · 524 lines · 0 tokens per session scan A ac6e92070b2a
baseplate is a skill published in the GitHub repository skyciv/skyciv-ai-skills (11 stars, last pushed 15d ago), licensed MIT. It adds 253 tokens to every session and 6,072 once invoked, about $0.0010 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.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.