- name
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add vibeeval/vibecosystem --skill agentica-claude-proxy -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add vibeeval/vibecosystem --skill agentica-claude-proxy -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add vibeeval/vibecosystem --skill agentica-claude-proxy -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add vibeeval/vibecosystem --skill agentica-claude-proxy -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/vibeeval/vibecosystem/tree/HEAD/skills/agentica-claude-proxyFrom the publisher
Use this skill when developing or debugging the Agentica-Claude proxy integration.
Agentica Agent → S_M_BASE_URL → Claude Proxy → claude -p → Claude CLI (with tools)
(localhost:2345) (localhost:8080)
Claude CLI in -p mode restricts file operations. You MUST add:
subprocess.run([
"claude", "-p", prompt,
"--append-system-prompt", system_prompt,
"--allowedTools", "Read", "Write", "Edit", "Bash", # REQUIRED
])
Without this, agents will report "permission denied" for Write/Edit operations.
Agentica expects SSE streaming, not plain JSON:
# Response format
yield f"data: {json.dumps(chunk)}\n\n"
yield "data: [DONE]\n\n"
Agents MUST return results as Python code blocks with a return statement:
return "your result here"
Agentica's REPL parser extracts code between ```python and ```.
Agents will hallucinate success without actually using tools unless you explicitly warn them:
## ANTI-HALLUCINATION WARNING
**STOP AND READ THIS CAREFULLY:**
You have access to these tools: Read, Write, Edit, Bash
When the task asks you to create/modify/run something:
1. FIRST: Actually invoke the tool (Read, Write, Edit, or Bash)
2. SECOND: Wait for the tool result
3. THIRD: Then return your answer based on what actually happened
**DO NOT** skip the tool invocation and just claim success!
If you didn't invoke a tool, you CANNOT claim the action succeeded.
Both Claude Code and Agentica have sandboxes:
/tmp/ paths are blocked by Claude CodeSolution: Use project-relative paths like workspace/ instead of /tmp/
cat logs/agent-<N>.log
Note: Logs only show final conversational response, not tool invocations.
curl -s http://localhost:8080/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model": "claude", "messages": [{"role": "user", "content": "Create file at workspace/test.txt"}], "stream": false}'
# After agent claims to create file
ls -la workspace/test.txt
cat workspace/test.txt
# Terminal 1: Proxy
uv run python scripts/agentica/claude_proxy.py --port 8080
# Terminal 2: Agentica Server
cd workspace/agentica-research/agentica-server
INFERENCE_ENDPOINT_URL=http://localhost:8080/v1/chat/completions uv run agentica-server --port 2345
S_M_BASE_URL=http://localhost:2345 uv run python your_script.py
curl http://localhost:8080/health # Proxy
curl http://localhost:2345/health # Agentica
scripts/agentica/claude_proxy.pyscripts/agentica/claude_proxy.py:49-155workspace/test_swarm_all_tools.pyscripts/agentica/dependency_swarm.pyGuide for integrating Agentica SDK with Claude Code CLI proxy
---name: agentica-claude-proxydescription: Guide for integrating Agentica SDK with Claude Code CLI proxy---# skills/agentica-claude-proxy/SKILL.mdFAQ
Download skills/agentica-claude-proxy/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/vibeeval/vibecosystem.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.