agentica-claude-proxy SKILL.md skillA

agentica-claude-proxy from vibeeval/vibecosystem is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add vibeeval/vibecosystem/agentica-claude-proxy@git:20260314.f0071a0

Pins git:20260314.f0071a0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
vibeeval/vibecosystem
Path
skills/agentica-claude-proxy/SKILL.md
Versions recorded
1
Latest version
git:20260314.f0071a0, committed Mar 14, 2026
Size
4,328 bytes
Repository stars
539
License
MIT

Guide for integrating Agentica SDK with Claude Code CLI proxy.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agentica-Claude Code Proxy Integration

Use this skill when developing or debugging the Agentica-Claude proxy integration.

## When to Use

- Setting up Agentica agents to use Claude Code tools
- Debugging agent hallucination issues
- Fixing permission errors in file operations
- Understanding the REPL response format

## Architecture Overview

```
Agentica Agent → S_M_BASE_URL → Claude Proxy → claude -p → Claude CLI (with tools)
                 (localhost:2345)   (localhost:8080)
```

## Critical Requirements

### 1. --allowedTools Flag (REQUIRED)

Claude CLI in `-p` mode restricts file operations. You MUST add:

```python
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.

### 2. SSE Streaming Format (REQUIRED)

Agentica expects SSE streaming, not plain JSON:

```python
# Response format
yield f"data: {json.dumps(chunk)}\n\n"
yield "data: [DONE]\n\n"
```

### 3. REPL Response Format (REQUIRED)

Agents MUST return results as Python code blocks with a return statement:

```python
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add vibeeval/vibecosystem/agentica-claude-proxy@sha256:c35e441660630154

The line at the top of this page pins the label git:20260314.f0071a0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7fjpx2wgtfmormwb.svg)](https://markdownregistry.com/a/art_7fjpx2wgtfmormwb)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Mar 14, 2026.

versioncommittedcommitsizeaudit
git:20260314.f0071a0 latest2026-03-14 f0071a0 4,328 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4328 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

vibeeval/vibecosystem · 539 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7fjpx2wgtfmormwb
GET https://markdownregistry.com/api/v1/resolve?ref=vibeeval/vibecosystem/agentica-claude-proxy
GET https://markdownregistry.com/api/v1/blob/c35e44166063015495bf200317549e35da725fe74c9f3d32d43f6d51d8e559f3

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from vibeeval/vibecosystem

agent-development Cursor rule
vibeeval/vibecosystem · .cursor/rules/agent-development.mdc · Rules for creating and editing vibecosystem agent definitions
git:20260330.cd5da78 · audit A · 539 stars
general Cursor rule
vibeeval/vibecosystem · .cursor/rules/general.mdc · vibecosystem core coding standards and quality rules
git:20260412.a904537 · audit A · 539 stars
hook-development Cursor rule
vibeeval/vibecosystem · .cursor/rules/hook-development.mdc · Rules for developing vibecosystem TypeScript hooks
git:20260330.cd5da78 · audit A · 539 stars
security Cursor rule
vibeeval/vibecosystem · .cursor/rules/security.mdc · Security rules for code review and vulnerability prevention
git:20260330.cd5da78 · audit A · 539 stars
skill-development Cursor rule
vibeeval/vibecosystem · .cursor/rules/skill-development.mdc · Rules for creating and editing vibecosystem skills
git:20260330.cd5da78 · audit A · 539 stars
testing Cursor rule
vibeeval/vibecosystem · .cursor/rules/testing.mdc · TDD workflow and testing standards
git:20260330.cd5da78 · audit A · 539 stars
AGENTS.md AGENTS.md file
vibeeval/vibecosystem · AGENTS.md
git:20260808.3b763b1 · audit A · 539 stars
accessibility-patterns SKILL.md skill
vibeeval/vibecosystem · skills/accessibility-patterns/SKILL.md · WCAG 2.2 AA compliance, ARIA patterns, keyboard navigation, screen reader optimization
git:20260412.a904537 · audit A · 539 stars
accessibility-testing SKILL.md skill
vibeeval/vibecosystem · skills/accessibility-testing/SKILL.md · axe-core integration, WCAG 2.2 AA checklist, keyboard navigation testing, screen reader testing, and ARIA pattern…
git:20260314.f0071a0 · audit A · 539 stars
achievements SKILL.md skill
vibeeval/vibecosystem · skills/achievements/SKILL.md · Steam-style achievement system with XP, levels, streaks, and skill trees. Gamifies the development workflow. 25…
git:20260408.85b86f4 · audit A · 539 stars
agent-benchmark SKILL.md skill
vibeeval/vibecosystem · skills/agent-benchmark/SKILL.md · Framework for measuring and tracking agent response quality over time. Detects regressions before they reach…
git:20260328.603ff34 · audit A · 539 stars
agent-context-isolation SKILL.md skill
vibeeval/vibecosystem · skills/agent-context-isolation/SKILL.md · Agent Context Isolation
git:20260314.f0071a0 · audit A · 539 stars

Every file in vibeeval/vibecosystem

Browse by kind, by grade A, or by owner.