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 skills add majiayu000/claude-skill-registry --skill 71-agent-framework-integrationgit clone --depth 1 https://github.com/majiayu000/claude-skill-registryWrote 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/majiayu000/claude-skill-registry/71-agent-framework-integration)<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/71-agent-framework-integration"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/71-agent-framework-integration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/71-agent-framework-integration"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/71-agent-framework-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 117 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 212 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00019 | $0.01718 |
| Opus 5 | $0.00010 | $0.00859 |
| Sonnet 5 | $0.00004 | $0.00344 |
| Haiku 4.5 | $0.00002 | $0.00172 |
Grade B, and why
71-agent-framework-integration scanned grade B 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 13d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills/agent-integration/ How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Your Agent Integration Skill
Your Task API model is deployed and running via Ollama. Now you need to connect it to agent frameworks like OpenAI Agents SDK, Claude Code, and MCP servers.
Before learning integration patterns, you will own an agent-integration skill. This skill becomes your reusable reference for connecting custom models to any framework.
This lesson follows the Skill-First Learning Pattern: build the skill, then learn what it knows.
Why Skill-First for Agent Integration?
Agent framework integration involves multiple interconnected patterns:
| Pattern | What It Handles |
|---|---|
| LiteLLM Proxy | Unified OpenAI-compatible API for any backend |
| Base URL Config | Redirect SDK calls to custom endpoints |
| Tool Calling | Structured outputs for function invocation |
| Error Fallback | Graceful degradation to foundation models |
| MCP Integration | Model Context Protocol server setup |
Learning these patterns without a reference leads to trial-and-error debugging. Your skill captures verified patterns from official documentation, giving you a reliable starting point.
Step 1: Get the Skills Lab
If you completed Chapter 70, you already have the skills-lab. If not:
- Go to github.com/panaversity/claude-code-skills-lab
- Click the green Code button
- Select Download ZIP
- Extract the ZIP file
- Open the extracted folder in your terminal
cd claude-code-skills-lab
claude
Step 2: Create Your Agent Integration Skill
Copy and paste this prompt:
Using your skill creator skill, create a new skill called "agent-integration"
for connecting custom LLM backends to agent frameworks.
I need patterns for:
- LiteLLM proxy configuration for OpenAI SDK compatibility
- OpenAI Agents SDK with custom base_url
- Tool calling with custom models (structured outputs)
- Error handling and fallback to foundation models
- MCP server integration with custom backends
Use context7 skill to study:
- OpenAI Python SDK documentation
- LiteLLM documentation
- FastMCP documentation
Build from official docs only, no assumed knowledge.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 239 lines · 19 tokens per session scan B 27106c0b4f91
71-agent-framework-integration is a skill published in the GitHub repository majiayu000/claude-skill-registry (604 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 1,718 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
remotion-docs
Search and fetch Remotion documentation pages.
remotion-captions
Dealing with captions in Remotion.
remotion-render
Best practices for rendering videos.
academy-guide
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude…
remotion-maps
Remotion Map animation knowledge.
mediabunny
Multimedia handling with the Mediabunny library.