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/adding-capabilitiesnpx skills add Artesiana/agent2 --skill adding-capabilitiesgit clone --depth 1 https://github.com/Artesiana/agent2What 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 | $0.00039 | $0.01182 |
| Opus 5 | $0.00019 | $0.00591 |
| Sonnet 5 | $0.00008 | $0.00236 |
| Haiku 4.5 | $0.00004 | $0.00118 |
Grade A, and why
adding-capabilities 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding Capabilities to Agents
Overview
Agent2 capabilities are opt-in. Start with a simple agent (schema + tools + prompt), then add capabilities as your use case requires them.
When to Activate
- User says "add resume", "add approval", "add knowledge", "add provider policy"
- Agent needs multi-turn conversations
- Agent needs human-in-the-loop before executing side effects
- Agent needs cost-optimized provider routing
- Agent needs per-request tool filtering
Capability Quick Reference
| Capability | When You Need It | What It Adds |
|---|---|---|
| Pause/Resume | Multi-turn workflows, clarification loops | message_history serialization |
| Approval Workflow | Human must approve before side effects | pending_actions + execute endpoint |
| Provider Policy | Cost control, prompt cache optimization | provider_order in config |
| Tool Scoping | Per-tenant or per-request tool filtering | Tool policy in before_run() |
| Knowledge Search | Agent needs domain documents | R2R + Knowledge MCP via toolsets= |
Pause/Resume
Add when: Agent needs to ask a question and wait for a human to answer before continuing.
1. Accept history in before_run
def before_run(input_data: dict) -> dict:
if input_data.get("message_history"):
input_data["_instructions"] = (
"Continue the conversation. Read the human's response and proceed."
)
return input_data
2. Persist history in after_run
The framework auto-serializes _message_history into the response. Your host product stores it wherever it wants (Redis, Postgres, Convex, etc.) and sends it back on the next call.
3. Advertise in config
capabilities:
- resume
Approval Workflow
Add when: Agent proposes side effects (send email, update records, make payments) that need human sign-off.
1. Return pending_actions from agent output or mock_result
def mock_result(input_data: dict) -> dict:
return {
"status": "needs_approval",
"pending_actions": [
{
"action": "send_email",
"params": {"to": "[email protected]", "body": "..."},
"description": "Send follow-up email to the client.",
}
],
}
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.
- 3d ago First seen · 182 lines · 39 tokens per session scan A 0c13676bd32c
adding-capabilities is a skill published in the GitHub repository Artesiana/agent2 (36 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 1,182 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 2026-08-30.
Other skills, from other repositories
crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
agent-tool
Add a new tool/function the AI agent can call (e.g. look something up, hit an external API, perform an action). Use when extending the assistant's capabilities, wiring a new function into the agent, or when the model needs a new action. This project uses {{ cookiecutter.aiframework }}.
openai-docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to…
skill-creator
Create new reusable skills from conversation context.
pydanticai-docs
Use this skill whenever the user is working with the Pydantic AI framework — including building AI agents, defining structured outputs with Pydantic models, wiring up tools/function calling, configuring model providers (OpenAI, Anthropic, Gemini, etc.), managing dependencies via agent context, handling streaming…