Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/vijayatechlabs/openstart/gemini-mdgit clone --depth 1 https://github.com/vijayatechlabs/openstartWhat 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 | $0.00181 | $0.00181 |
| Opus 5 | $0.00090 | $0.00090 |
| Sonnet 5 | $0.00036 | $0.00036 |
| Haiku 4.5 | $0.00018 | $0.00018 |
Grade A, and why
openstart 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 3d 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
GEMINI.md
This project uses the VijayaTech Project Framework. All AI operating instructions are centralized in one file so every agent — Gemini and Google AntiGravity included — behaves consistently.
→ Read and follow .ai/framework/AGENT-GUIDE.md first.
It defines: which .ai/docs/ docs to read at session start, how to operate, where
to write documentation (.ai/framework/DOC-RULES.md), the AEO/SEO standard
(.ai/framework/aeo/AEO-FRAMEWORK.md), and how to onboard / adopt / update a
project — follow .ai/framework/ONBOARD.md.
Do not duplicate instructions here — edit .ai/framework/AGENT-GUIDE.md so all agents
stay in sync.
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.
- 3d ago First seen · 16 lines · 181 tokens per session scan A 15111b53080a
openstart GEMINI.md is an instructions file published in the GitHub repository vijayatechlabs/openstart (5 stars, last pushed 4d ago), licensed MIT. It adds 181 tokens to every session, about $0.0009 per session on Opus 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.
Other instructions, from other repositories
eGEOagents AGENTS.md
Instructions for mverab/eGEOagents, covering openspec instructions, agents.md, project: e-geo (generative engine optimization), quick start and available commands.
claude-rank CLAUDE.md
Instructions for Houseofmvps/claude-rank, covering claude-rank, project overview, architecture, tech stack and conventions.
skills AGENTS.md
Instructions for sinch/skills, covering agents.md, repository purpose, how to discover and use skills, skill format and contributing.
citlyze-mcp GEMINI.md
Gemini CLI instructions for Citlyze/citlyze-mcp: Citlyze tracks how brands show up in AI search: ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews, and more. This extension connects Gemini CLI to the workspace behind the API key in CITLYZEAPIKEY.
kai-cmo-harness AGENTS.md
AGENTS.md instructions for cgallic/kai-cmo-harness, covering agents.md — kai marketing os, instruction contract (critical), goals over procedures, runtime primitives and quick start.
kai-cmo-harness CLAUDE.md
Claude Code instructions for cgallic/kai-cmo-harness: Claude Code reads this file; the canonical agent context lives in AGENTS.md (single source of truth for all agents). At session start, also read memory/MEMORY.md. Load-on-demand detail is in .claude/rules/.