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 instructions/ibuilder/massing/agents-mdgit 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 | $0.01132 | $0.01132 |
| Opus 5 | $0.00566 | $0.00566 |
| Sonnet 5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
massing AGENTS.md 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
check: `curl http://localhost:8000/health` → `{"status":"ok"}`. How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Cursor Cloud specific instructions
This section is for Cloud Agents running in an environment where the startup update script has
already installed dependencies. It captures the non-obvious bits of running Massing here; standard
commands and product detail live in the README, docs/getting-started.md, and the .claude/skills/.
What the update script already did
- Installed the web workspace deps (
npm install, which also runsapps/webpredevWASM copy). - Ensured Node 24 is installed via
nvm(the repo requiresnode >=24; Node 18 breaks the web build). - Installed the Python API deps into the user site (
~/.local):services/api/requirements.lock(runtime, hash-pinned, py3.12/Linux — matches prod) andservices/api/requirements-dev.txt(test/lint: httpx, ruff, bandit, pytest, coverage, DracoPy).services/data's deps are a strict subset of the lock, so there is no separate install for it.
Services (all run from source in dev)
| Service | Path | Dev run command | Port |
|---|---|---|---|
| Web (Vite + TS viewer/authoring UI) | apps/web |
npm run dev |
5173 |
API (FastAPI; bundles the services/data ifcopenshell library) |
services/api |
uvicorn aec_api.main:app --reload |
8000 |
Postgres + MinIO are not needed for dev: the API defaults to SQLite (sqlite:///./aec.db) and
local filesystem storage. Docker/docker compose --profile full is the self-host path, not required
here. The converter (Node IFC→Fragments) is job-style/optional — the API reconverts in-process on publish.
Node 24 gotcha (important)
/exec-daemon/node (v22) sits first on PATH and shadows nvm's Node 24 even after nvm use 24.
Before any web command, put Node 24 first explicitly:
export NVM_DIR="$HOME/.nvm"; . "$NVM_DIR/nvm.sh"; export PATH="$(nvm which 24 | xargs dirname):$PATH"
node -v # must print v24.x
Running the two dev servers
Start each in its own long-lived terminal (e.g. tmux). The web app in dev calls the API at
http://localhost:8000 (see apps/web/src/api/httpCore.ts); CORS default already allows the Vite origin.
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 · 67 lines · 1,132 tokens per session scan A c03eb8d98e54
massing AGENTS.md is an instructions file published in the GitHub repository ibuilder/massing (132 stars, last pushed 2d ago), licensed MIT. It adds 1,132 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
solibri-mcp CLAUDE.md
Claude Code instructions for Vanderjohnny/solibri-mcp, covering instruções para agentes (claude code, claude desktop), 1. regra geral: dados, não pixels, quando um print é legítimo, 2. solibri: use a api, nunca a tela and se as ferramentas falharem.
conway AGENTS.md
AGENTS.md instructions for bldrs-ai/conway, covering agents.md, build and test, pr lifecycle, review: codex first, sub-agent on timeout and what the draft gate covers.
opentakeoff AGENTS.md
Instructions for Kentucky-ai/opentakeoff, covering run / build / check, shipping — the required steps, every change, where things live, how the canvas works (the mental model) and conventions.
rvt-mcp AGENTS.md
Instructions for bimwright/rvt-mcp, covering agents.md — rvt-mcp install guide for ai agents, rules for agents, baked-tool routing, prerequisites (check first, stop if any are missing) and step 1 — download the client setup zip.
rvt-mcp CLAUDE.md
Instructions for bimwright/rvt-mcp, covering rvtmcp-mcp, architecture, project structure, build & deploy and build everything (server + all 6 plugin shells).
archsight-aios GEMINI.md
Instructions for ArchSightLabs/archsight-aios, covering gemini.md, 必读入口 and gemini 特别说明.