Borrowing it
Nothing to install: this file belongs to kranthik123/Gemini-Ralph-Loop. 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/kranthik123/Gemini-Ralph-Loop/main/GEMINI.mdgit clone --depth 1 https://github.com/kranthik123/Gemini-Ralph-LoopWrote 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/kranthik123/gemini-ralph-loop/gemini-md)<a href="https://agentmods.dev/instructions/kranthik123/gemini-ralph-loop/gemini-md"><img src="https://agentmods.dev/badge/instructions/kranthik123/gemini-ralph-loop/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/kranthik123/gemini-ralph-loop/gemini-md"><img src="https://agentmods.dev/badge/instructions/kranthik123/gemini-ralph-loop/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 | $0.00318 | $0.00318 |
| Opus 5.5 | $0.00127 | $0.00127 |
| Sonnet 5.5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
Gemini-Ralph-Loop 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.
What it actually says
Ralph Loop - Autonomous Development Loop
Ralph Loop enables iterative, self-referential development where you work on a task repeatedly until completion. Your work persists between iterations.
State Management
Ralph Loop stores state in .ralph-state/ directory:
.ralph-state/state.json- Current loop state.ralph-state/history.json- Iteration history.ralph-state/checkpoints/- Saved checkpoints
State File Format
.ralph-state/state.json:
{"id": "loop-
Commands
/ralph:start-loop <task> - Start a new loop
/ralph:status - Check current status
/ralph:pause - Pause the loop
/ralph:resume - Resume paused loop
/ralph:complete - Mark as completed
/ralph:cancel - Cancel the loop
/ralph:history - View iteration history
/ralph:checkpoint <name> - Create checkpoint
/ralph:restore <name> - Restore checkpoint
/ralph:reset - Clear all state
/ralph:help - Show help
Workflow
Start: /ralph:start-loop "Build a REST API"
Work iteratively, updating .ralph-state/state.json after each step
When done, output: <done>COMPLETE </done>
Important Rules
Always read .ralph-state/state.json before making changes Increment iteration counter after each meaningful progress Files you create persist between iterations Use checkpoints before risky changes
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 · 47 lines · 318 tokens per session scan A 5c162ea19980
Gemini-Ralph-Loop GEMINI.md is an instructions file published in the GitHub repository kranthik123/Gemini-Ralph-Loop (58 stars, last pushed 10mo ago), licensed MIT. It adds 318 tokens to every session, about $0.0013 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-Ralph-Loop GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Gemini-Ralph-Loop GEMINI.mdkranthik123/Gemini-Ralph-Loop | Instructions file | 58 | 10mo ago | MIT | A | 318 | 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 | 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 |