open-responses-agent-dev

open-responses-agent-dev is a skill for Claude Code from OthmanAdi/open-responses-agent-skill. It costs 46 tokens per session (4,084 once invoked), scanned A, original, MIT.

A development guide for building autonomous agents with the Open Responses API through Hugging Face Inference Providers. It uses one endpoint and can route requests to different providers by adding a provider suffix to the model name.

In plain words
What is it for?
Use it when building agents with the OpenAI SDK, Hugging Face-hosted models, tool-using sub-agents, or provider-specific model routing.
Why use it?
It reduces the need to write separate integrations for each supported model provider. It is intended for multi-step agent workflows and can expose the agent's reasoning process.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the open-responses-agent-dev plugin — 1 skill shipped together

Good fit Use it when building agents with the OpenAI SDK, Hugging Face-hosted models, tool-using sub-agents, or provider-specific model routing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/othmanadi/open-responses-agent-skill/open-responses-agent-dev
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 OthmanAdi/open-responses-agent-skill --skill open-responses-agent-dev
Clone the repo
git clone --depth 1 https://github.com/OthmanAdi/open-responses-agent-skill

Made for: Claude Code.

Or install open-responses-agent-dev, the plugin that ships this one along with the rest of its 1 skill.

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 open-responses-agent-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/othmanadi/open-responses-agent-skill/open-responses-agent-dev.svg)](https://agentmods.dev/skills/othmanadi/open-responses-agent-skill/open-responses-agent-dev)
Your own site
<a href="https://agentmods.dev/skills/othmanadi/open-responses-agent-skill/open-responses-agent-dev"><img src="https://agentmods.dev/badge/skills/othmanadi/open-responses-agent-skill/open-responses-agent-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,084 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 $0.00046 $0.04084
Opus 5 $0.00023 $0.02042
Sonnet 5 $0.00009 $0.00817
Haiku 4.5 $0.00005 $0.00408

Measured 7d ago against content hash 488f89445461, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

open-responses-agent-dev 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 7d 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.

skills/open-responses-agent-dev/SKILL.md · 663 lines

How it starts

The opening of the file, as written. The whole thing — 663 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open Responses Agent Development

Build autonomous agents with the Open Responses API - the open-source standard for multi-provider, agentic LLM interfaces via HuggingFace Inference Providers.

When to Use This Skill

Activate this skill when:

  • Building autonomous agents (not chatbots)
  • Need multi-step workflows in a single request
  • Want multi-provider routing with a single endpoint
  • Need reasoning visibility (see agent thinking)
  • Building sub-agent loops with tools
  • Want to use the OpenAI SDK with open-source models

Key Concept: Single Unified Endpoint

IMPORTANT: Open Responses uses ONE unified endpoint with provider routing via model suffixes.

Endpoint: https://router.huggingface.co/v1
Model format: model-id:provider (e.g., moonshotai/Kimi-K2-Instruct-0905:groq)

Providers are specified as suffixes on the model name:

  • :groq - Groq inference
  • :together - Together AI
  • :nebius - Nebius AI
  • :auto - Automatic provider selection
  • (no suffix) - Default provider

Core Concepts

1. The Responses Endpoint

POST https://router.huggingface.co/v1/responses
Authorization: Bearer $HF_TOKEN
Content-Type: application/json

Request Structure:

{
  "model": "moonshotai/Kimi-K2-Instruct-0905:groq",
  "instructions": "You are a helpful assistant.",
  "input": "User request",
  "tools": [...],
  "tool_choice": "auto",
  "reasoning": { "effort": "medium" },
  "stream": false
}

Response Structure:

{
  "id": "resp_abc123",
  "model": "moonshotai/Kimi-K2-Instruct-0905:groq",
  "output": [
    { "type": "reasoning", "content": "Let me think..." },
    { "type": "function_call", "name": "search", "arguments": "{...}" },
    { "type": "function_call_output", "output": "..." },
    { "type": "message", "content": "Final response" }
  ],
  "output_text": "Final response",
  "usage": { "input_tokens": 100, "output_tokens": 200 }
}

2. Sub-Agent Loops

The API automatically handles:

  1. Model samples a response
  2. Emits tool calls if needed
  3. Executes tools (for server-side tools like MCP)
  4. Feeds results back
  5. Repeats until completion

Read the full file on GitHub · 663 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. 7d ago First seen · 663 lines · 46 tokens per session scan A 488f89445461

Subscribe to this mod's changes

open-responses-agent-dev is a skill published in the GitHub repository OthmanAdi/open-responses-agent-skill (3 stars, last pushed 7mo ago), licensed MIT. It adds 46 tokens to every session and 4,084 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.

Related

Other skills, from other repositories

recall

Reconstruct and narrate the current development context from contextual commits. Run at session start, when resuming work, or when switching branches. Produces a brief, conversational summary of where things stand.

berserkdisruptors/contextual-commits · 43 tokens

workspace-ralph-orchestrator

Orchestrate Ralph automation loops for spec-driven development. Use when starting, stopping, monitoring, or checking status of Ralph loops. Triggers on Ralph start, Ralph stop, Ralph status, spec automation, task loop, run tasks, check progress, kill Ralph, resume Ralph, or tmux session management.

T-0-co/t-0-spec-kit-ralph · 70 tokens

autonomous-longtask-v2

Guide for long, autonomous development tasks with Claude Code. Optimized patterns for multi-session tasks, Tasks system, sub-agents, parallelization, and loop-closing. Use for complex features (multiple files/services), multi-step workflows (5+ dependent steps), long-running tasks (>30 min), or multi-session work that…

T-0-co/t-0-spec-kit-ralph · 75 tokens

autonomous-longtask

Guide für lange, autonome Entwicklungsaufgaben mit Claude Code. Optimierte Patterns für Multi-Session-Tasks, Sub-Agents, Parallelisierung und Loop-Closing.

T-0-co/t-0-spec-kit-ralph · 38 tokens

autogpt-agents

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

Orchestra-Research/AI-Research-SKILLs · 39 tokens

autonomous-loop

Use when a set-up project (project/BRIEF.md approved, PROFILE/STATE/backlog present) should continue building autonomously — orchestration of CEO/PO/DEV/REVIEWER cycles with parallel agents, without user input. Also for resuming after an interruption or handoff.

BechsteinDigital/claude-shiploop · 63 tokens