Borrowing it
Nothing to install: this file belongs to ksprashu/gemini-cli-config. 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/ksprashu/gemini-cli-config/main/AGENTS.mdgit clone --depth 1 https://github.com/ksprashu/gemini-cli-configWrote 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/ksprashu/gemini-cli-config/agents-md)<a href="https://agentmods.dev/instructions/ksprashu/gemini-cli-config/agents-md"><img src="https://agentmods.dev/badge/instructions/ksprashu/gemini-cli-config/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/ksprashu/gemini-cli-config/agents-md"><img src="https://agentmods.dev/badge/instructions/ksprashu/gemini-cli-config/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 | $0.07314 | $0.07314 |
| Opus 5.5 | $0.02926 | $0.02926 |
| Sonnet 5.5 | $0.01463 | $0.01463 |
| Haiku 4.5 | $0.00731 | $0.00731 |
Grade A, and why
gemini-cli-config 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 — 483 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User-Provided Instructions & Overrides
This document provides explicit, project-specific instructions that override or supplement the core system prompt. Follow these directives without exception.
1. The Protocol Handshake (Mandatory Boot Sequence)
To ensure you are always operating with the latest instructions and to prevent context drift, every non-trivial task MUST begin with the Protocol Handshake.
The user will initiate this by starting their prompt with the // GO GEMINI directive.
Upon receiving this directive, you MUST perform the following steps before addressing the user's task:
- Read Instructions: Reload the entire user defined mandate from @AGENTS.md
- Generate Protocol Checksum: Identify all H2 (##) headers in the document and list them.
- Acknowledge and Engage: Respond to the user with the following format:
Protocol Sync Complete. Acknowledged <X> core directives: - <Header 1> - <Header 2> - ... Now beginning task: "<The user's task description summarised and paraphrased>" - Proceed: Immediately begin the task by following "The Core Cognitive Framework".
This handshake is not optional. It is the mandatory boot sequence for your cognitive framework on every task.
2. The Unwavering Adherence Mandate (Pre-flight Checklist)
To prevent protocol deviation, the first thought of every sequentialthinking plan for a non-trivial task MUST be a Pre-flight Checklist. This checklist is non-negotiable.
Action:
- Acknowledge the user's goal.
- Explicitly state that you will use the Core Cognitive Framework (Deconstruct, Plan, Execute).
- Confirm that you will show your work, including the task list with status emojis.
Example First Thought:
goal: The user wants to refactor the authentication module. I will use the Core Cognitive Framework to ensure a safe and transparent process. I will deconstruct the problem, create a detailed plan, execute it, and show my work using the live task list.
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 · 483 lines · 7,314 tokens per session scan A b5796776bdef
gemini-cli-config AGENTS.md is an instructions file published in the GitHub repository ksprashu/gemini-cli-config (22 stars, last pushed 12d ago), licensed Apache-2.0. It adds 7,314 tokens to every session, about $0.0293 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.
gemini-cli-config AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gemini-cli-config AGENTS.mdksprashu/gemini-cli-config | Instructions file | 22 | 12d ago | Apache-2.0 | A | 7,314 | 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 |