Borrowing it
Nothing to install: this file belongs to LTplus-AG/ifc-lite. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LTplus-AG/ifc-lite/main/AGENTS.mdgit clone --depth 1 https://github.com/LTplus-AG/ifc-liteWrote 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/instructions/ltplus-ag/ifc-lite/agents-md)<a href="https://agentmods.dev/instructions/ltplus-ag/ifc-lite/agents-md"><img src="https://agentmods.dev/badge/instructions/ltplus-ag/ifc-lite/agents-md/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/instructions/ltplus-ag/ifc-lite/agents-md"><img src="https://agentmods.dev/badge/instructions/ltplus-ag/ifc-lite/agents-md.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 | $0.10746 | $0.10746 |
| Opus 5.5 | $0.04298 | $0.04298 |
| Sonnet 5.5 | $0.02149 | $0.02149 |
| Haiku 4.5 | $0.01075 | $0.01075 |
Grade A, and why
ifc-lite AGENTS.md 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 4d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines: ifc-lite
Project-specific guardrails. This file is the source of truth; CLAUDE.md and .cursorrules point here.
What this is
Browser-first IFC toolkit: a WebGPU web viewer plus a headless CLI/MCP/server. No first-party desktop app. Domain logic (decode, geometry, styling, export) lives in Rust crates under rust/* and is the source of truth for the server, CLI, SDK, and wasm; TypeScript packages under packages/* and apps under apps/* consume it (TS mostly does GPU upload and UI). Architecture docs: docs/architecture/overview.md.
Accountability, and what a PR has to be able to answer
Everything here is agent-written; there is no AI-disclosure rule. Submitters must answer for the code.
Every PR has an accountable submitter, and the test is answering, not authorship. When review asks a question, the submitter answers with evidence: a test, a run, a measurement, a model file that reproduces it. "The agent wrote it" is never an answer. "Here is the run that proves it" always is. You do not need to be able to write the code. You do need to be able to demonstrate what it does. Unanswered questions block the merge.
A PR claiming user-visible behaviour shows that behaviour. Not "should work". For this repo that usually means a real IFC model from a real authoring tool, an oracle run, or a viewer screenshot: ground truth an agent cannot fabricate, and the contribution it cannot make. Supplying one is worth more than another sweep.
Work selection
Default lane: a PR closes an issue carrying the ready label. ready means the maintainer has decided it is in scope, wanted now, and scoped. scripts/check-issue-queue.mjs checks this and prints its own mode; read that line, not this one, because no prose here tracks a config key. The escape hatch is the unqueued label, applied by the maintainer.
Filing issues is welcome and unrestricted: an audit producing twenty good issue reports is a real contribution. Filing is not claiming, and an unlabelled issue is not a work item.
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.
- 4d ago Changed · +11 tokens per session 411c62a5d1d3
- 5d ago Changed · +4 lines · +24 tokens per session 47a9d14dc899
- 6d ago Changed · -24 tokens per session b6c240029ae8
- 7d ago Changed 9baa9e046330
- 8d ago Changed · -5 lines · -79 tokens per session 7716600f8638
- 9d ago Changed · +4 lines · +7 tokens per session 7c7d9522d950
- 21d ago Changed · +13 tokens per session 00e7a9134abb
- 25d ago Changed · -7 lines · -45 tokens per session d23cdee6221a
- 1mo ago Changed · -12 tokens per session 958760c7198a
- 1mo ago First seen · 278 lines · 10,851 tokens per session scan A ac543b8b59cc
ifc-lite AGENTS.md is an instructions file published in the GitHub repository LTplus-AG/ifc-lite (461 stars, last pushed today), licensed MPL-2.0. It adds 10,746 tokens to every session, about $0.0430 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 2026-08-30.
ifc-lite AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ifc-lite AGENTS.mdLTplus-AG/ifc-lite | Instructions file | 461 | today | MPL-2.0 | A | 10,746 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |