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 skills/ibuilder/massing/ship-releasenpx skills add ibuilder/massing --skill ship-releasegit clone --depth 1 https://github.com/ibuilder/massingWhat 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 | $0.00074 | $0.02265 |
| Opus 5 | $0.00037 | $0.01132 |
| Sonnet 5 | $0.00015 | $0.00453 |
| Haiku 4.5 | $0.00007 | $0.00227 |
Grade A, and why
ship-release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship a Massing release
Standing directions for this repo: docs/roadmap-directions.md. Read those first.
main is unprotected and ships version-numbered releases via direct commits (no PR gate). Each shippable change is its own release. Follow this exactly.
1. Verify before you ship
- Backend (services/api, services/data): run the affected
test_*.py(see thebackend-testsskill) and ruff exactly as CI does:
A file-levelcd services/api && python -m ruff check src/ ../data/src/ruff check <file>from elsewhere does NOT pick upservices/api/ruff.toml(isort/I001) and gives false "passed". Preferruff check --fixto auto-sort imports; put third-party imports in their own group after stdlib. - Web (apps/web):
export PATH="/c/Program Files/nodejs:$PATH"thennpm run typecheck && npm run lint && npm run build(Node 24; Node 18 breaks the build). Runnpx vitest run <path>if unit tests cover the change. - Frontend UI: the dev-preview geometry loader stalls at "preparing geometry", so verify rail UI via the
verify-frontendskill (forcebuildToolsPanelby dispatchingaec:persona), and flag any flow you couldn't exercise end-to-end.
2. Bump the version — THREE files, and the third is not edited by hand
git fetch origin --quiet # avoid the version race (a background release may have taken the next number)
sed -i 's/"version": "0.3.X"/"version": "0.3.Y"/' apps/web/package.json apps/web/src-tauri/tauri.conf.json
cd apps/web && npm install --package-lock-only --ignore-scripts && cd - # re-syncs package-lock.json
package-lock.json carries the version too — twice, at the root and under
packages["apps/web"] — and versionConsistency.test.ts asserts all of them agree. This step said
"BOTH files" until 2026-07-29, when a release ran the two seds and went red on a lock nobody had
mentioned. Regenerating the lock is the fix rather than a third sed: hand-editing it would sync the
number while leaving whatever else the bump touched stale.
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.
- 2d ago First seen · 134 lines · 74 tokens per session scan A 18a112dc92e4
ship-release is a skill published in the GitHub repository ibuilder/massing (132 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 2,265 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
ara3d-sdk
Use when processing AEC/BIM 3D data in .NET 8 — mesh generation and transformation, SIMD-accelerated math, IFC/STEP/PLY to glTF/GLB/VIM conversion, plugin development. Ara3D-SDK: high-performance .NET 3D geometry and BIM library suite.
elements
Use when generating building information models (BIM) programmatically in C#/.NET — wall, beam, column, floor creation, geometry kernel (BREP/CSG), glTF/IFC/JSON serialization, MEP systems, spatial grids. Hypar Elements: the smallest useful BIM — a cross-platform C# library for creating building elements without…
fy_layout
Use when doing construction site layout planning with the FeiYang LightCAD platform — fence, lawn, foundation pit, road, prefab house 2D/3D modeling. FYLayout: construction site layout secondary development plugin for LightCAD/LightBIM.
xbim
Use when processing BIM/IFC data in .NET/C# — IFC reading/writing, model validation, quantity takeoff, geometry extraction. xBIM: .NET BIM/IFC toolkit for building information modeling workflows.
3d-skills
Use when working with 3D Gaussian Splatting (3DGS), .ply model cleanup/compression/publishing, interactive 360-degree panorama visualization and virtual tours, AEC/BIM 3D data processing, or CSG solid modeling. Index of 5 skills: SuperSplat, Photo-Sphere-Viewer, Ara3D-SDK, Elements, and OpenCSG.NET.
aios-arch
架构评审工作流。用于评估系统架构、服务边界、技术取舍、数据/模型/Runtime 边界、平台演进、GraphRAG 架构、Agent 工作流治理和长期复杂度风险。.