Borrowing it
Nothing to install: this file belongs to JTCHE/houdini-mcp. 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/JTCHE/houdini-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/JTCHE/houdini-mcpWrote 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/jtche/houdini-mcp/agents-md)<a href="https://agentmods.dev/instructions/jtche/houdini-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jtche/houdini-mcp/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/jtche/houdini-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jtche/houdini-mcp/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 | $0.00490 | $0.00490 |
| Opus 5.5 | $0.00196 | $0.00196 |
| Sonnet 5.5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
houdini-mcp 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 1mo 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project information: @README.md
Read Mission first. It says what this server is for and what shape a change must take. Every other rule here serves it.
Guides
- Mission — few tools, many shapes; execute is the last resort.
- Issues — where the specs live, and how to work from them.
- Architecture — the three layers, and which file owns what.
- Deployment — this repo is canonical; Houdini reads copies.
- Code — one source of truth, small modules, no legacy paths.
- Testing — test the change in your own session, do not commit the test.
- Houdini API — the API is the authority, not your memory.
Rules
- Use ASD-STE100 Simplified Technical English in all writing: replies, comments, commits, pull requests.
- Do not keep backward compatibility. Delete the old path. Do not add fallbacks, shims, or migrations.
- Do not write documentation that a person can get from the code. Write a short comment in the code instead.
- Do not record a fact that goes stale: tool counts, version numbers, file inventories, status tables, audit results. Point to the code that holds it.
- Do not add a file to this repo unless the product needs it. Scratch work goes in a temporary directory.
- Do not commit or publish SideFX content or any other copyrighted material. This includes help pages, images from the Houdini install, and test fixtures made from them. Make a fixture on the machine that runs the test.
- Look at the change in a live Houdini before you report it done. Code that imports is not a plugin that answers. See Deployment: Houdini runs a copy, so run the installer and restart the plugin first. Start your own session; never work in the Houdini the user has open.
- When a change answers a spec, append a dated line to it and set
Status: Closed.
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.
- 1mo ago Changed · +9 tokens per session 80e63927e441
- 1mo ago Changed · +1 tokens per session fb8592bcdffc
- 1mo ago Changed · +6 lines · +108 tokens per session a85ffdd9d7be
- 1mo ago Changed · +6 lines · +102 tokens per session 8f87424362c9
- 2mo ago First seen · 26 lines · 270 tokens per session scan A 30a7d79a1544
houdini-mcp AGENTS.md is an instructions file published in the GitHub repository JTCHE/houdini-mcp (15 stars, last pushed yesterday), licensed MIT. It adds 490 tokens to every session, about $0.0020 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.
houdini-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| houdini-mcp AGENTS.mdJTCHE/houdini-mcp | Instructions file | 15 | yesterday | MIT | A | 490 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |