symbi-agent-sdk

symbi-agent-sdk is a skill for Claude Code, Codex from ThirdKeyAI/symbi-gemini-cli. It costs 48 tokens per session (573 once invoked), scanned A, original, Apache-2.0.

A development guide for wrapping Gemini CLI agents in Symbiont's ORGA governance system. Gemini CLI is Google's command-line agent, while governance controls its tools, limits, permissions, and records.

In plain words
What is it for?
Use it to create governed Gemini agents, define their allowed capabilities, connect them to Symbiont's executor, and set execution policies.
Why use it?
It provides a defined way to run headless agents under sandboxing, budgets, access policies, and auditing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Gemini CLI.

Good fit Use it to create governed Gemini agents, define their allowed capabilities, connect them to Symbiont's executor, and set execution policies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thirdkeyai/symbi-gemini-cli/symbi-agent-sdk
Install

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.

Any agent
npx skills add ThirdKeyAI/symbi-gemini-cli --skill symbi-agent-sdk
Clone the repo
git clone --depth 1 https://github.com/ThirdKeyAI/symbi-gemini-cli

Made for: Claude Code, Codex.

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.

agentmods badge for symbi-agent-sdk

README.md
[![agentmods](https://agentmods.dev/badge/skills/thirdkeyai/symbi-gemini-cli/symbi-agent-sdk.svg)](https://agentmods.dev/skills/thirdkeyai/symbi-gemini-cli/symbi-agent-sdk)
Your own site
<a href="https://agentmods.dev/skills/thirdkeyai/symbi-gemini-cli/symbi-agent-sdk"><img src="https://agentmods.dev/badge/skills/thirdkeyai/symbi-gemini-cli/symbi-agent-sdk.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 573 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00573
Opus 5 $0.00024 $0.00287
Sonnet 5 $0.00010 $0.00115
Haiku 4.5 $0.00005 $0.00057

Measured 8d ago against content hash 518f00567c12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

symbi-agent-sdk 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 8d 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:

skills/symbi-agent-sdk/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini CLI + ORGA Integration

Help the user create Gemini CLI agents that are governed by Symbiont's ORGA loop.

Architecture

In the runtime-first (Mode B) pattern, Symbiont's CliExecutor spawns Gemini CLI as a governed subprocess:

Symbiont Runtime (ORGA Loop)
  -> CliExecutor (sandbox + budget)
    -> Gemini CLI (execution)
      -> symbi extension (awareness bridge)
        -> parent MCP server (governance tools)

DSL Executor Block

When the user wants to define a Gemini CLI agent in DSL, use the executor block:

agent task_name(input: InputType) -> OutputType {
    capabilities = ["read", "analyze", "write"]

    executor {
        type = "gemini_cli"
        allowed_tools = ["read_file", "write_file", "run_shell_command", "symbi__*"]
        extension = "symbi"
        model = "gemini-2.5-pro"
    }

    policy access_policy {
        allow: read(any) if true
        deny: write(any) if not input.approved
        audit: all_operations
    }

    with sandbox = "tier1", timeout = "30m" {
        result = execute(input)
        return result
    }
}

CliExecutor Environment Variables

When Symbiont spawns Gemini CLI, these environment variables are set:

Variable Purpose
SYMBIONT_MANAGED=true Signals the extension is inside a managed runtime
SYMBIONT_MCP_URL HTTP endpoint to connect back to parent MCP server
SYMBIONT_RUNTIME_SOCKET Unix socket for runtime communication
SYMBIONT_SESSION_ID Unique session ID for audit correlation
SYMBIONT_BUDGET_TOKENS Token budget for this execution
SYMBIONT_BUDGET_TIMEOUT Timeout for this execution

Workflow

  1. Ask what the agent should do and its security requirements
  2. Create the DSL definition with an executor block for gemini_cli
  3. Define Cedar policies for the agent's capabilities
  4. Generate the symbiont.toml configuration if needed
  5. Validate with symbi__parse_dsl
  6. Explain how to run: symbi run <agent_name> --prompt "..."

Read the full file on GitHub · 72 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.

  1. 8d ago First seen · 72 lines · 48 tokens per session scan A 518f00567c12

Subscribe to this mod's changes

symbi-agent-sdk is a skill published in the GitHub repository ThirdKeyAI/symbi-gemini-cli (3 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 573 once invoked, about $0.0002 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.