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 skills/artesiana/agent2/creating-agentsnpx skills add Artesiana/agent2 --skill creating-agentsgit clone --depth 1 https://github.com/Artesiana/agent2Wrote 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/skills/artesiana/agent2/creating-agents)<a href="https://agentmods.dev/skills/artesiana/agent2/creating-agents"><img src="https://agentmods.dev/badge/skills/artesiana/agent2/creating-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 5.1 | $0.00050 | $0.00902 |
| Opus 5 | $0.00025 | $0.00451 |
| Sonnet 5 | $0.00010 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
creating-agents scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:<port>/health # Health check How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Agents
Overview
Scaffold a complete Agent2 agent service. One agent = one schema, one API, one Docker service.
If the requested agent is a domain expert, regulated workflow, document reviewer,
compliance worker, or professional brain clone, use brain-clone first and
study agents/procurement-compliance-officer.
When to Activate
- User says "create agent", "new agent", "scaffold agent", "add agent"
- User describes a use case that needs a new agent service
- User wants to add a new backend AI worker
Steps
1. Gather Requirements
Ask the user:
- Name (kebab-case, e.g.
support-ticket) - What it does (one sentence)
- Output fields (what the structured result should contain)
- Tools needed (what the agent should be able to call)
- Knowledge needed? (does it need to search documents?)
2. Generate Files
Create all files in agents/<name>/:
| File | What to put |
|---|---|
__init__.py |
Empty |
schemas.py |
Pydantic BaseModel with Field() descriptions. Use Literal for enums, validators for constraints. |
tools.py |
One function per tool. Include docstrings. Stub implementations. |
agent.py |
create_agent() with instructions= and @agent.tool_plain registrations |
config.yaml |
name, description, model (empty = use DEFAULT_MODEL), port, timeout, collections |
main.py |
from shared.api import create_app; app = create_app("<name>") |
Dockerfile |
Copy from agents/example-agent/Dockerfile, change agent paths |
tests/promptfoo/<name>/eval.yaml |
For domain agents, behavior-level evals |
3. Key Rules
# agent.py — ALWAYS use instructions=, NEVER system_prompt=
agent = create_agent(
name="my-agent",
output_type=MySchema,
instructions="You are...",
toolsets=[knowledge_server] if needs_knowledge else [],
)
# Tools — ALWAYS @agent.tool_plain, delegate to tools.py
@agent.tool_plain
def my_tool(arg: str) -> dict:
"""Docstring is the tool description the LLM sees."""
return tools.my_tool(arg)
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 · 93 lines · 50 tokens per session scan A 0678bca274d6
creating-agents is a skill published in the GitHub repository Artesiana/agent2 (36 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 902 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.
rag-knowledge
Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…
alembic-migration
Create, review, and apply database schema changes with Alembic. Use whenever a SQLAlchemy model is added or changed, a column/index/constraint needs to change, or a data backfill is required — anything that alters the PostgreSQL schema.
billing-stripe
Work with Stripe billing — subscriptions, plans/prices, the Customer Portal, credits, usage metering, invoices, and webhook events. Use when changing plans, handling a new Stripe webhook, debugging a payment/subscription flow, or touching credit balances and usage.
video_action_recognition
本技能为基于视频的人体动作识别算法提供技术规范与实现指导。 适用于需要从视频中检测和分类人体动作、且不依赖 LLM 或模型训练的场景。.