What is symbi-gemini-cli GEMINI.md?

Project instructions for symbi-gemini-cli, a command-line tool with rules for governed AI agents. They explain its trust model, policy files, agent definitions, available tools, and repository conventions.

Use them when working on Symbiont governance, Cedar policies, DSL agent files, MCP tools, repository conventions, or Gemini CLI behavior.

They give the agent the project context needed to work within its authorization and verification rules. They also describe the two operating modes and where project guidance comes from.

How ThirdKeyAI/symbi-gemini-cli configures Gemini CLI

Reuse

Borrowing it

Nothing to install: this file belongs to ThirdKeyAI/symbi-gemini-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ThirdKeyAI/symbi-gemini-cli/main/GEMINI.md

Clone the repo

git clone --depth 1 https://github.com/ThirdKeyAI/symbi-gemini-cli

Made for: Gemini CLI.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/thirdkeyai/symbi-gemini-cli/gemini-md/github.svg)](https://agentmods.dev/instructions/thirdkeyai/symbi-gemini-cli/gemini-md)

Your own site

<a href="https://agentmods.dev/instructions/thirdkeyai/symbi-gemini-cli/gemini-md"><img src="https://agentmods.dev/badge/instructions/thirdkeyai/symbi-gemini-cli/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/thirdkeyai/symbi-gemini-cli/gemini-md"><img src="https://agentmods.dev/badge/instructions/thirdkeyai/symbi-gemini-cli/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,005 This file is loaded in full into every session.

When invoked 1,005 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01005	$0.01005
Opus 5.5	$0.00402	$0.00402
Sonnet 5.5	$0.00201	$0.00201
Haiku 4.5	$0.00101	$0.00101

Measured 1mo ago against content hash b8b027b9cc88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

symbi-gemini-cli 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 1mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

symbi-gemini-cli GEMINI.md — 100% identical, 0 lines differ

GEMINI.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Symbiont Governance Context

This environment uses the Symbiont trust stack for AI agent governance.

Key Concepts

ORGA Loop: Observe -> Reason -> Gate -> Act. The Gate phase operates outside LLM influence and cannot be bypassed. Phase transitions are enforced at compile time via Rust's type system.
Cedar Policies: Authorization rules controlling what agents and tools can do. Files use .cedar extension. Evaluation at <1ms.
SchemaPin: Cryptographic verification of MCP tool schemas (ECDSA P-256). Ensures tools haven't been tampered with. Uses Trust-On-First-Use (TOFU) key pinning.
AgentPin: Domain-anchored cryptographic identity for AI agents (ES256 JWT, 12-step verification).
DSL: Symbiont's domain-specific language for defining agents declaratively. Files use .dsl extension.

Available MCP Tools (via symbi server)

invoke_agent -- Run a Symbiont agent with a prompt (params: agent, prompt, system_prompt?)
list_agents -- List available agents from .dsl files in agents/ directory
parse_dsl -- Parse and validate DSL files (params: file? or content?)
get_agent_dsl -- Read an agent's DSL definition (params: agent)
get_agents_md -- Get the project's AGENTS.md content
verify_schema -- Verify a tool schema with SchemaPin (params: schema, public_key_url)

File Conventions

Agent definitions: agents/*.dsl
Cedar policies: policies/*.cedar
Symbiont config: symbiont.toml
Agent manifests: AGENTS.md

Dual-Mode Operation

The extension operates in two modes, detected automatically via environment variables:

Mode A -- Standalone (extension-first)

Developer installs the extension directly. Gemini CLI loads hooks/MCP/skills. The extension spawns its own symbi mcp server. Policy enforcement is advisory plus Gemini CLI's native policy engine.

Mode B -- ORGA-managed (runtime-first)

Symbiont's CliExecutor spawns Gemini CLI as a governed subprocess. The extension detects SYMBIONT_MANAGED=true and defers to the outer ORGA Gate for hard enforcement. The inner extension provides awareness.

Read the full file on GitHub · 80 lines

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.

1mo ago First seen · 80 lines · 1,005 tokens per session scan A b8b027b9cc88

Subscribe to this mod's changes

symbi-gemini-cli GEMINI.md is an instructions file published in the GitHub repository ThirdKeyAI/symbi-gemini-cli (3 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 1,005 tokens to every session, about $0.0040 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 2026-08-31.

Building agents agents agentskills ai gemini gemini-cli governance

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).

microsoft/vscode · 9,715 tokens

symbi-gemini-cli: Instructions file for Gemini CLI