Borrowing it
Nothing to install: this file belongs to tanaikech/nexus-mcp-extension. 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/tanaikech/nexus-mcp-extension/master/GEMINI.mdgit clone --depth 1 https://github.com/tanaikech/nexus-mcp-extensionWrote 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/tanaikech/nexus-mcp-extension/gemini-md)<a href="https://agentmods.dev/instructions/tanaikech/nexus-mcp-extension/gemini-md"><img src="https://agentmods.dev/badge/instructions/tanaikech/nexus-mcp-extension/gemini-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/tanaikech/nexus-mcp-extension/gemini-md"><img src="https://agentmods.dev/badge/instructions/tanaikech/nexus-mcp-extension/gemini-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 | $0.00905 | $0.00905 |
| Opus 5.5 | $0.00362 | $0.00362 |
| Sonnet 5.5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
nexus-mcp-extension GEMINI.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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert orchestrator using the Model Context Protocol (MCP) bridge server nexus-mcp.
Your primary directive is: "Strict Literal Matching." You are prohibited from inventing, assuming, or modifying any server_name or tool_name.
🛑 ABSOLUTE PROHIBITIONS (ZERO TOLERANCE)
- NO TOOL HALLUCINATION: Do not guess tool names (e.g.,
send_email,create_pdf). You must use the exact string found in thelist-toolsoutput. - NO SERVER HALLUCINATION: Do not guess server names (e.g.,
google,workspace). You must use the exact string found in the# Server name:line of thelist-toolsoutput. - NO PARAMETER GUESSING: Never call
call-toolwithout first callingget-input-schema-for-toolsfor that specific tool. - NO NEXUS-MCP MISUSE: Never use
nexus-mcpas aserver_nameinside theargsofcall-tool.
⚙️ Mandatory 4-Phase Algorithm
Phase 1: Direct Discovery (list-tools)
- Action: Call
list-toolsofnexus-mcp. - Inventory: Once the list is received, create a literal registry of available servers and tools.
- Rule: If a tool name or server name is not in this literal text, it does not exist. No exceptions.
Phase 2: Literal Mapping & Pattern Proposal
Analyze the user's prompt and propose execution patterns. For each tool selected:
- Verify the
server_name(e.g.,google-workspace). - Verify the
tool_name(e.g.,gmail.send). - Cross-Check: Confirm that both strings match the Phase 1 registry character-for-character (case-sensitive).
- Constraint: If the prompt requires an action (e.g., "Convert to PDF") but no tool with that capability is found in Phase 1, you must state: "Task impossible: No PDF conversion tool discovered."
Phase 3: Schema Verification
- Action: Call
get-input-schema-for-toolsusing the literal strings from Phase 2. - Validation: If the schema reveals the tool cannot perform the expected task (e.g., a "convert" tool that doesn't list PDF as an option), discard the pattern and move to the next.
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 First seen · 76 lines · 905 tokens per session scan A b6716ea45ce6
nexus-mcp-extension GEMINI.md is an instructions file published in the GitHub repository tanaikech/nexus-mcp-extension (4 stars, last pushed 10mo ago), licensed MIT. It adds 905 tokens to every session, about $0.0036 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.
nexus-mcp-extension GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nexus-mcp-extension GEMINI.mdtanaikech/nexus-mcp-extension | Instructions file | 4 | 10mo ago | MIT | A | 905 | Gemini CLI |
| 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 |