Neuro SAN Studio is a hands-on environment for building, testing, and deploying networks of collaborating AI agents with the Neuro SAN framework. Developers, researchers, and domain experts use its examples, tutorials, and declarative HOCON configuration to prototype multi-agent applications. The catalogue instructions support workflows for using this studio and framework.
Borrowing it
Nothing to install: this file belongs to cognizant-ai-lab/neuro-san-studio. 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/cognizant-ai-lab/neuro-san-studio/main/AGENTS.mdgit clone --depth 1 https://github.com/cognizant-ai-lab/neuro-san-studioWrote 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/cognizant-ai-lab/neuro-san-studio/agents-md)<a href="https://agentmods.dev/instructions/cognizant-ai-lab/neuro-san-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/cognizant-ai-lab/neuro-san-studio/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/cognizant-ai-lab/neuro-san-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/cognizant-ai-lab/neuro-san-studio/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 | $0.01631 | $0.01631 |
| Opus 5.5 | $0.00652 | $0.00652 |
| Sonnet 5.5 | $0.00326 | $0.00326 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
neuro-san-studio 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Rules for coding agents in Neuro-san-studio.
Neuro SAN Studio is a multi-agent orchestration framework built on the
neuro-san library.
Agent networks are defined declaratively in HOCON files under registries/.
Custom Python tools live in coded_tools/.
1. Contribution rules
- Check the toolbox before writing Python. toolbox_info.hocon already provides web search, RAG, code execution, Gmail, Jira and more.
- Every network sets
max_stepsandmax_execution_seconds; never leave them unbounded. Older networks that lack them are not precedent. - No secrets in HOCON: use the environment or
.env. Never log or printsly_data. - Add optional dependencies in
coded_tools/<group>/<agent_network>/requirements.txt, and keep the network disabled by default in the manifest. - Review any internet-sourced agent skill before use; a
SKILL.mdcan reference untrusted tools. - Keep the diff focused: no unrequested refactors and no reformatting of untouched files. Review it before creating a
PR and remove debug prints, commented-out code, stray
TODOs and files touched by accident. - Documentation ships in the same PR. A curated example (
basic/,industry/,tools/) requiresmetadata, documentation asdocs/examples/<group>/<agent_network>.md, a line and a TOC entry in examples.md, and a registered fixture. A feature updates its own reference document instead: toolbox.md, plugins.md, search_tools.md, or user_guide.md → Middleware. A network ingenerated/is git-ignored and personal. Verify every link in the documents you touch to check for broken links. - Use US spelling for English words.
2. Coding style
- Clean Code Standards: follow Robert C. Martin’s (Uncle Bob) Clean Code and The Clean Coder recommendations
- Keep things simple, to the point, readable, maintainable and individually testable.
- Line length: 119 characters, both for .py and .md files.
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 · +20 lines · +231 tokens per session e9207d6c1d4d
- 1mo ago Changed · +2 lines · +49 tokens per session 3ad4752b1813
- 1mo ago First seen · 86 lines · 1,351 tokens per session scan A 7b2df30eb9ab
neuro-san-studio AGENTS.md is an instructions file published in the GitHub repository cognizant-ai-lab/neuro-san-studio (1,194 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,631 tokens to every session, about $0.0065 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 2026-09-23.
neuro-san-studio AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| neuro-san-studio AGENTS.mdcognizant-ai-lab/neuro-san-studio | Instructions file | 1.2k | yesterday | Apache-2.0 | A | 1,631 | 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 | today | 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 |