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 agents/sixb-ai/sixb/defining-agentsgit clone --depth 1 https://github.com/sixb-ai/sixbWrote 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/agents/sixb-ai/sixb/defining-agents)<a href="https://agentmods.dev/agents/sixb-ai/sixb/defining-agents"><img src="https://agentmods.dev/badge/agents/sixb-ai/sixb/defining-agents.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 | $0.00000 | $0.01600 |
| Opus 5 | $0.00000 | $0.00800 |
| Sonnet 5 | $0.00000 | $0.00320 |
| Haiku 4.5 | $0.00000 | $0.00160 |
Grade A, and why
defining-agents 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 today.
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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Defining agents
defineAgent(id, config) creates an agent. The id is its stable identifier (used in routes and
threads) and must be unique across all agents. The call validates the config and returns an
AgentDefinition you export from agents/.
// agents/invoice-assistant.ts
import { defineAgent } from "@sixb/core"
import { gateway } from "ai"
export const invoiceAssistant = defineAgent("invoice-assistant", {
name: "Invoice Assistant",
description: "Tracks outstanding invoices, overdue accounts, and payment follow-ups.",
model: gateway("openai/gpt-5.5"),
reasoning: "medium",
instructions: [
"You are this project's invoicing assistant.",
"Focus on invoices, balances, due dates, and reminder status.",
"Never claim a reminder was sent unless the data shows it.",
].join("\n"),
providerOptions: {
openai: { reasoningSummary: "detailed" },
},
})
Config
| Field | Type | Required | Description |
|---|---|---|---|
name |
string |
Yes | Display name shown in catalogs and pickers. |
model |
LanguageModelV4 |
Yes | An AI SDK model instance (see below). |
instructions |
string |
Yes | The system prompt. |
description |
string |
No | Short summary for catalogs. |
reasoning |
reasoning level | No | provider-default, none, minimal, low, medium, high, or xhigh. |
providerOptions |
provider-keyed object | No | Per-provider passthrough, e.g. { openai: { ... } }. |
groups |
GroupDefinition[] |
No | Gate who can use the agent and what it can reach. See Authorization. |
tools |
AgentToolDefinition[] |
No | Worker-side tools this agent is explicitly allowed to call. Defaults to none. |
loop |
AgentLoopConfig |
No | Step cap, prompt caching, and optional context-budget overrides. |
The model
model is an AI SDK LanguageModelV4 instance, not a string. The simplest
source is the ai gateway; any provider that returns a LanguageModelV4 works.
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.
- today Changed · +58 lines 1c07f2e843df
- 4d ago First seen · 117 lines · 0 tokens per session scan A 9e77e8c6402a
defining-agents is an agent published in the GitHub repository sixb-ai/sixb (60 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,600 tokens. 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 2026-08-30.
Other agents, from other repositories
librarian
Researches external libraries and APIs by reading source code. Returns definitive, source-verified answers.
reviewer
Code review specialist for quality/security analysis.
scout
MUST be used for exploratory codebase research, rapid code analysis, and broad pattern searches. Fast read-only scout returning compressed context for handoff.
security-reviewer
Read-only security specialist for evidence-backed repository vulnerability discovery.
init
Generate AGENTS.md for current codebase.
cavecrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is caveman-compressed so the main thread eats 60% fewer tokens than vanilla Explore. Refuses to suggest fixes.