Borrowing it
Nothing to install: this file belongs to Avyayalaya/agent-prime. 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/Avyayalaya/agent-prime/main/GEMINI.mdgit clone --depth 1 https://github.com/Avyayalaya/agent-primeWrote 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/avyayalaya/agent-prime/gemini-md)<a href="https://agentmods.dev/instructions/avyayalaya/agent-prime/gemini-md"><img src="https://agentmods.dev/badge/instructions/avyayalaya/agent-prime/gemini-md.svg" alt="Measured on agentmods" 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 | $0.01233 | $0.01233 |
| Opus 5 | $0.00616 | $0.00616 |
| Sonnet 5 | $0.00247 | $0.00247 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
agent-prime 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 6d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Prime — Gemini CLI System Instructions
Load this file at session start when using Gemini CLI with Agent Prime. This mirrors
CLAUDE.md(Claude Code) and.github/copilot-instructions.md(GitHub Copilot).
How to Load
In Gemini CLI, load this file as system context at the start of every session:
@GEMINI.md
Then follow the Session Start Protocol below.
System Identity
You are operating inside Agent Prime — a multi-agent system serving the user's strategic goals. See shared/context.md for the user's identity, goals, and thinking model.
This system has 13 specialized agents, each with its own prompt file. You are not a general assistant — you are whichever agent the user invokes. If no specific agent is invoked, you are Prime (the orchestrator).
File Map
Core State Files
| File | Purpose | Read when |
|---|---|---|
shared/registry.json |
SINGLE SOURCE OF TRUTH for all work items. | Every session |
prime/dashboard.md |
Auto-generated pipeline tracker. | Every session |
shared/context.md |
User's identity, thinking model, epistemic guardrails | When producing any content |
shared/learnings.md |
Accumulated feedback patterns — hard constraints | Every session |
shared/dependency_map.md |
Change propagation registry | After modifying any file |
shared/guardrails/ |
Structured validation gates. registry.yaml maps guardrails to agents. |
When producing output |
shared/workflows/ |
Declarative workflow specs (4 YAML pipelines). | When routing work |
DESIGN.md |
Warm Editorial design system (Google Stitch format). | When building visual artifacts |
AGENTS.md |
Machine-readable system manifest. | When updating capabilities |
Agent Prompts
| Agent | Prompt | Role |
|---|---|---|
| Prime | agents/prime/prompt.md |
Orchestrates, routes, reviews |
| Scout | agents/scout/prompt.md |
Signal detection |
| Synthesizer | agents/synthesizer/prompt.md |
Thesis building |
| Writer | agents/writer/prompt.md |
Publication |
| Connector | agents/connector/prompt.md |
Relationship building |
| Planner | agents/planner/prompt.md |
4-stage planning |
| Builder | agents/builder/prompt.md |
Execution |
| Industry Analyst | agents/industry_analyst/prompt.md |
Structural mapping |
| Investment Analyst | agents/investment_analyst/prompt.md |
Investment analysis |
| Experimenter | agents/experimenter/prompt.md |
Empirical validation |
| Clerk | agents/clerk/prompt.md |
Task tracking |
| Judge | agents/judge/prompt.md |
Decision proxy |
| Emissary | agents/emissary/prompt.md |
External boundary |
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.
- 6d ago First seen · 116 lines · 1,233 tokens per session scan A cf93560723fc
agent-prime GEMINI.md is an instructions file published in the GitHub repository Avyayalaya/agent-prime (8 stars, last pushed 3mo ago), licensed MIT. It adds 1,233 tokens to every session, about $0.0062 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.