Skip to content
mcp/skillhub

Agent Skill

Agentica Claude Proxy skill

agentica-claude-proxyparcadei/Continuous-Claude-v3.claude/skills/agentica-claude-proxy/SKILL.md

Guide for integrating Agentica SDK with Claude Code CLI proxy

3.9kMIT

always on

19 tokname + description

once used

1,005 tokSKILL.md body

bundled files

0

repo stars

3.9kGitHub

Install the Agentica Claude Proxy skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/parcadei/Continuous-Claude-v3 --skill agentica-claude-proxy

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git /tmp/Continuous-Claude-v3
mkdir -p ~/.claude/skills
cp -R /tmp/Continuous-Claude-v3/.claude/skills/agentica-claude-proxy ~/.claude/skills/agentica-claude-proxy

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description19 tok
When the agent uses itThe SKILL.md instructions1,005 tok
Only if openedNo bundled files—

Until it is used, agentica-claude-proxy costs about 72× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 150 skills from parcadei/Continuous-Claude-v3 would load 2,175 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Pre-approved tools (allowed-tools): Read, Bash. The agent can use these without asking while the skill is active.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Agentica-Claude Code Proxy Integration
  • When to Use
  • Architecture Overview
  • Critical Requirements
  • 1. --allowedTools Flag (REQUIRED)
  • 2. SSE Streaming Format (REQUIRED)
  • 3. REPL Response Format (REQUIRED)
  • Anti-Hallucination Prompt Engineering
  • Path Sandboxing
  • Debugging
  • Check Agent Logs
  • Test Proxy Directly
  • Verify File Operations
  • Server Commands
  • Start Servers
  • Use Swarm
  • Health Checks
  • Reference Files
  • Common Errors

More skills from parcadei/Continuous-Claude-v3

All skills in this repo
  1. agentica-infrastructureparcadei/Continuous-Claude-v3

    Reference guide for Agentica multi-agent infrastructure APIs

    3.9k14 tok idle · 686 in use
  2. agentica-promptsparcadei/Continuous-Claude-v3

    Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

    3.9k21 tok idle · 1,701 in use
  3. agentica-sdkparcadei/Continuous-Claude-v3

    Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

    3.9k23 tok idle · 2,798 in use
  4. agentica-serverparcadei/Continuous-Claude-v3

    Agentica server + Claude proxy setup - architecture, startup sequence, debugging

    3.9k18 tok idle · 1,062 in use
  5. analytic-functionsparcadei/Continuous-Claude-v3

    Problem-solving strategies for analytic functions in complex analysis

    3.9k12 tok idle · 952 in use
  6. ast-grep-findparcadei/Continuous-Claude-v3

    AST-based code search and refactoring via ast-grep MCP

    3.9k17 tok idle · 673 in use
  7. banach-spacesparcadei/Continuous-Claude-v3

    Problem-solving strategies for banach spaces in functional analysis

    3.9k15 tok idle · 905 in use
  8. boundary-value-problemsparcadei/Continuous-Claude-v3

    Problem-solving strategies for boundary value problems in odes pdes

    3.9k17 tok idle · 1,083 in use