Borrowing it
Nothing to install: this file belongs to vinhnx/vtchat. 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/vinhnx/vtchat/main/GEMINI.mdgit clone --depth 1 https://github.com/vinhnx/vtchatWrote 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/vinhnx/vtchat/gemini-md)<a href="https://agentmods.dev/instructions/vinhnx/vtchat/gemini-md"><img src="https://agentmods.dev/badge/instructions/vinhnx/vtchat/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/vinhnx/vtchat/gemini-md"><img src="https://agentmods.dev/badge/instructions/vinhnx/vtchat/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 | $0.00544 | $0.00544 |
| Opus 5.5 | $0.00218 | $0.00218 |
| Sonnet 5.5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
vtchat 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 today.
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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Agent Guide (Concise)
This guide is streamlined to reduce context size. Use AGENTS.md for the authoritative repository guidelines.
Key Practices
- Bun for all tasks; no npm/yarn.
- 4-space indent, single quotes, 100-char line.
- PascalCase components; camelCase hooks/utils; kebab-case files; named exports.
- Use enums for reusable keys; configuration via environment variables only.
- UI follows shadcn/ui minimal principles; neutral palette; minimal icons.
HTTP Client Guidelines
- Use ky HTTP client only:
import { http } from '@repo/shared/lib/http-client' - Never use fetch directly - bypasses security and standardization
- GET:
const data = await http.get('/api/endpoint') - POST:
const result = await http.post('/api/endpoint', { body: data }) - Streaming:
const response = await http.postStream('/api/completion', { body, signal }) - API keys:
http.post('/api/external', { body, apiKeys: { openai: 'sk-...' } })
Structure & Commands
- Apps in
apps/(Next.js inapps/web); shared packages inpackages/(@repo/ui,@repo/shared,@repo/common). - Tests live in
apps/web/app/tests/. - Common commands:
bun install,bun dev,bun run build,bun run lint,bun run fmt,bun test.
Deployment & Logging
- Never run
./deploy-fly.shwithout explicit approval. - Use
logfrom@repo/shared/lib/logger; avoidconsole.*.
React Best Practices
- For comprehensive
useEffectbest practices, examples, and anti-patterns, see docs/react-effect.md.
Refer to AGENTS.md for complete details.
URL Context + Grounding (Gemini)
When your prompt contains one or more URLs, the Gemini web search task automatically enables Google’s URL Context tool alongside Google Search grounding. The model retrieves content from those URLs (if supported and safe) and uses it to enhance the answer. Retrieved URLs are surfaced in the Sources stack when available.
Notes
- Works with Gemini 3 family used for web search (Flash, Pro, Flash Lite).
- Up to 20 URLs per request; unsupported/paywalled URLs are skipped by Google.
- Retrieved content counts toward input tokens per Google pricing/limits.
- Gemini 3 Flash Lite always requires a user-supplied Gemini API key (no server-managed 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.
- today First seen · 49 lines · 544 tokens per session scan A 6ce3956fb24c
vtchat GEMINI.md is an instructions file published in the GitHub repository vinhnx/vtchat (59 stars, last pushed 1mo ago), licensed MIT. It adds 544 tokens to every session, about $0.0022 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 2026-10-15.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).