03-api

A REST API reference for an agent server. A REST API lets software communicate with the server over standard web requests, while JWT bearer tokens are signed credentials used to authenticate those requests.

In plain words
What is it for?
Use it to check service health, authenticate requests, list agents, execute agents and workflows, and create, update, or delete definitions through the API.
Why use it?
It explains how to securely call the server and manage agents, tools, and workflows. It also documents the permissions required for different operations.

Agent

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.

agentmods
npx agentmods add agents/jazzmind/busibox/03-api
Clone the repo
git clone --depth 1 https://github.com/jazzmind/busibox
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.06417
Opus 5 $0.00007 $0.03209
Sonnet 5 $0.00003 $0.01283
Haiku 4.5 $0.00001 $0.00642

Measured 2d ago against content hash 833b1c824ba1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

03-api 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 2d 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.

docs/developers/services/agents/03-api.md · 1,086 lines

How it starts

The opening of the file, as written. The whole thing — 1,086 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Server API Reference

Overview

The agent server provides a REST API for AI agent execution, tool orchestration, workflow management, and intelligent query routing.

Base URL: http://agent-lxc:8000
Authentication: JWT Bearer token
Content-Type: application/json

Authentication

All endpoints require a JWT Bearer token in the Authorization header:

Authorization: Bearer <jwt-token>

Required Scopes

  • agent.execute - Execute agents and workflows
  • agent.read - Read agent/tool/workflow definitions
  • agent.write - Create/update/delete definitions
  • admin.read - Admin read access
  • admin.write - Admin write access

Endpoints

Health Check

GET /health

Check service health.

Authentication: Not required

Response:

{
  "status": "ok"
}

Status Codes:

  • 200 OK - Service healthy
  • 503 Service Unavailable - Service unhealthy

Agent Management

GET /agents

List all agents (built-in + personal).

Authentication: Required
Scopes: agent.read

Query Parameters:

  • is_builtin (boolean, optional) - Filter by built-in status
  • is_active (boolean, optional) - Filter by active status

Response:

[
  {
    "id": "uuid",
    "name": "chat_agent",
    "display_name": "Chat Agent",
    "instructions": "You are a helpful assistant",
    "model": "agent",
    "tools": {"names": ["search_tool", "ingest_tool"]},
    "workflows": {"names": []},
    "scopes": ["search.read", "ingest.write"],
    "is_builtin": true,
    "created_by": null,
    "version": 1,
    "is_active": true,
    "created_at": "2025-12-12T10:00:00Z",
    "updated_at": "2025-12-12T10:00:00Z"
  }
]

Status Codes:

  • 200 OK - Success
  • 401 Unauthorized - Invalid/missing token
  • 403 Forbidden - Insufficient permissions
POST /agents/definitions

Create a new personal agent.

Authentication: Required
Scopes: agent.write

Request Body:

{
  "name": "my_agent",
  "display_name": "My Personal Agent",
  "instructions": "You are my personal assistant",
  "model": "agent",
  "tools": {"names": ["search_tool"]},
  "workflows": {"names": []},
  "scopes": ["search.read"]
}

Read the full file on GitHub · 1,086 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. 2d ago First seen · 1,086 lines · 14 tokens per session scan A 833b1c824ba1

Subscribe to this mod's changes

03-api is an agent published in the GitHub repository jazzmind/busibox (7 stars, last pushed 4d ago), licensed MIT. It adds 14 tokens to every session and 6,417 once invoked, about $0.0001 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.

Related

Other agents, from other repositories