Borrowing it
Nothing to install: this file belongs to Platano78/smart-ai-bridge. 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/Platano78/smart-ai-bridge/main/AGENTS.mdgit clone --depth 1 https://github.com/Platano78/smart-ai-bridgeWrote 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/platano78/smart-ai-bridge/agents-md)<a href="https://agentmods.dev/instructions/platano78/smart-ai-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/platano78/smart-ai-bridge/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/platano78/smart-ai-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/platano78/smart-ai-bridge/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 | $0.01576 | $0.01576 |
| Opus 5.5 | $0.00630 | $0.00630 |
| Sonnet 5.5 | $0.00315 | $0.00315 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
smart-ai-bridge 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 2mo 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Smart AI Bridge
Instructions for AI agents and agentic harnesses. Two audiences, in order:
- Consuming this project — installing and running it as an MCP server. Start here.
- Working on this repo — where code lives and what the hard rules are.
Everything below is verified against the code at v2.15.0. If something here disagrees with the code, the code wins and this file is a bug.
Part 1 — Install and run (for a harness onboarding this as a tool)
What this is
An MCP server (stdio transport, ESM Node.js) that gives an MCP client 17 tools for token-saving file operations, multi-AI orchestration, and code review. It routes each request across local and cloud LLM backends.
Requirements
- Node.js >= 18.0.0 (enforced via
enginesinpackage.json) - An MCP client that speaks stdio
- No API key is required to install, start, or list tools. A backend is only needed to actually execute a tool call.
Install
There is no npm package. Install by cloning:
git clone https://github.com/Platano78/smart-ai-bridge.git
cd smart-ai-bridge
npm install
npm test # expect all tests passing, 0 failures
Run
node /absolute/path/to/smart-ai-bridge/src/server.js
- stdout carries MCP JSON-RPC only. Never write to stdout from this codebase; it corrupts the protocol stream. All diagnostics go to stderr.
- The server starts and serves
tools/list(17 tools) with no backends configured. - On startup it runs a readiness audit to stderr. A backend whose key is unset is reported as
cannot verify — <KEY> not set. That is not an error and not a failed install.
Register with a client
Use an absolute path; relative paths depend on the client honoring cwd. Copy
.mcp.json.example, or:
{
"mcpServers": {
"smart-ai-bridge": {
"command": "node",
"args": ["/absolute/path/to/smart-ai-bridge/src/server.js"],
"env": { "NVIDIA_API_KEY": "your-key" }
}
}
}
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.
- 2mo ago Changed · +3 lines · +71 tokens per session f5071f7f3f2c
- 2mo ago First seen · 154 lines · 1,505 tokens per session scan A 985a435270f9
smart-ai-bridge AGENTS.md is an instructions file published in the GitHub repository Platano78/smart-ai-bridge (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,576 tokens to every session, about $0.0063 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.
smart-ai-bridge AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| smart-ai-bridge AGENTS.mdPlatano78/smart-ai-bridge | Instructions file | 2 | 2mo ago | Apache-2.0 | A | 1,576 | 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 |