How should claude-code be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this skill.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Crawler Summary

claude-code answer-first brief

Interface with Claude Code for code development, debugging, and codebase navigation. Use when needing to build features from natural language descriptions, debug and fix issues, navigate and understand codebases, generate code with file system access, or run complex development tasks requiring multiple tools. --- name: claude-code description: Interface with Claude Code for code development, debugging, and codebase navigation. Use when needing to build features from natural language descriptions, debug and fix issues, navigate and understand codebases, generate code with file system access, or run complex development tasks requiring multiple tools. --- Claude Code Quick Start Use Claude Code for AI-powered code developmen Capability contract not published. No trust telemetry is available yet. Last updated 4/14/2026.

Freshness

Last checked 4/14/2026

Best For

claude-code is best for openai workflows where MCP and OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB OPENCLEW, runtime-metrics, public facts pack

Card Facts Snapshot Contract Trust

Claim this agent

Agent DossierGitHubSafety: 94/100

claude-code

MCPself-declared

OpenClawself-declared

Public facts

Change events

Artifacts

Freshness

Apr 14, 2026

Verifiededitorial-contentNo verified compatibility signals

Capability contract not published. No trust telemetry is available yet. Last updated 4/14/2026.

Trust evidence available

Trust score

Unknown

Compatibility

MCP, OpenClaw

Freshness

Apr 14, 2026

Vendor

Hangoutlin Wq

Artifacts

Benchmarks

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Capability contract not published. No trust telemetry is available yet. Last updated 4/14/2026.

View Source

Setup snapshot

git clone https://github.com/hangoutlin-wq/openclaw-claude-code-skill.git

1
Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
2
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content

Vendor (1)

Vendor

Hangoutlin Wq

profilemedium

Observed Apr 14, 2026Source link Provenance

Compatibility (1)

Protocol compatibility

MCP, OpenClaw

contractmedium

Observed Apr 14, 2026Source link Provenance

Security (1)

Handshake status

UNKNOWN

trustmedium

Observed unknownSource link Provenance

Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium

Observed Apr 15, 2026Source link Provenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB OPENCLEW

Extracted files

Examples

Snippets

Languages

typescript

Parameters

Executable Examples

bash

scripts/claude_prompt.sh "your prompt here"

bash

scripts/claude_continue.sh

bash

scripts/run_claude.sh [options] [prompt]

bash

scripts/claude_prompt.sh "Create a Python REST API with Flask that has endpoints for users and products"

bash

scripts/claude_prompt.sh "Fix the bug in app.py where the user authentication fails"

bash

scripts/claude_prompt.sh "Explain how the authentication flow works in this project"

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

Full README

name: claude-code description: Interface with Claude Code for code development, debugging, and codebase navigation. Use when needing to build features from natural language descriptions, debug and fix issues, navigate and understand codebases, generate code with file system access, or run complex development tasks requiring multiple tools.

Claude Code

Quick Start

Use Claude Code for AI-powered code development with full file system access.

Non-interactive (recommended for OpenClaw):

scripts/claude_prompt.sh "your prompt here"

Continue previous conversation:

scripts/claude_continue.sh

Full interactive mode:

scripts/run_claude.sh [options] [prompt]

Key Capabilities

1. Build Features

Describe what you want to build in plain English. Claude Code will:

Create a plan
Write the code
Test and ensure it works

Example:

scripts/claude_prompt.sh "Create a Python REST API with Flask that has endpoints for users and products"

2. Debug and Fix Issues

Describe a bug or paste error messages. Claude Code will:

Analyze the codebase
Identify the problem
Implement a fix

Example:

scripts/claude_prompt.sh "Fix the bug in app.py where the user authentication fails"

3. Navigate Codebases

Ask anything about your codebase. Claude Code maintains awareness of:

Entire project structure
File relationships
Web searches for up-to-date info
External data sources via MCP

Example:

scripts/claude_prompt.sh "Explain how the authentication flow works in this project"

Common Workflows

Adding a New Feature

# Step 1: Describe the feature
scripts/claude_prompt.sh "Add user authentication with JWT tokens"

# Step 2: Continue conversation to refine
scripts/claude_continue.sh "Also add password reset functionality"

# Step 3: Continue to test and fix
scripts/claude_continue.sh "Run tests and fix any issues"

Debugging a Problem

# Step 1: Describe the issue with context
scripts/claude_prompt.sh "The API returns 500 error when POSTing to /api/users"

# Step 2: Continue to apply fix
scripts/claude_continue.sh "Fix the bug you found"

# Step 3: Continue to verify
scripts/claude_continue.sh "Run the tests to confirm the fix works"

Code Review and Refactoring

scripts/claude_prompt.sh "Review the utils.py file for performance issues and security vulnerabilities"
scripts/claude_continue.sh "Refactor the code you identified as problematic"

Configuration

Claude Code reads configuration from:

~/.claude/settings.json - API keys, model settings
~/.claude.json - User preferences
.claude/settings.json - Project-specific settings

Current setup:

Model: Configured via ANTHROPIC_BASE_URL (supports OpenAI-compatible APIs)
API Key: Set in ~/.claude/settings.json
Tools: Full access to Bash, Edit, Read, and more

Important Notes

Directory Safety

Claude Code should only be run in trusted directories. In print mode (-p), workspace trust dialog is skipped.

Session Management

Sessions are persisted automatically
Use --continue or -c to resume recent conversations
Use --resume [session-id] to resume a specific session

Output Formats

Default: Interactive terminal output
--print or -p: Print and exit (non-interactive)
--output-format json: JSON output for programmatic use
--output-format stream-json: Real-time streaming JSON

Resource Limits

Set maximum API spend:

scripts/claude_prompt.sh --max-budget-usd 1.0 "your prompt"

Advanced Usage

Custom System Prompt

scripts/run_claude.sh --system-prompt "You are a security-focused code reviewer" "Review this code"

Model Selection

scripts/run_claude.sh --model claude-sonnet-4-5 "your prompt"

Tool Restrictions

scripts/run_claude.sh --allowed-tools "Bash(git:*,npm:*),Read" "your prompt"

Custom Agents

scripts/run_claude.sh --agent '{"name": "reviewer", "description": "Code reviewer", "prompt": "You are a code reviewer"}' "Review this code"

Troubleshooting

Claude Code not found

Ensure npm package is installed:

npm ls -g @anthropic-ai/claude-code

API Authentication errors

Check ~/.claude/settings.json for correct ANTHROPIC_AUTH_TOKEN and ANTHROPIC_BASE_URL.

Session not resuming

Use --resume with session ID:

scripts/run_claude.sh --resume <session-id>

Resources

scripts/

run_claude.sh - Full Claude Code wrapper
claude_prompt.sh - Non-interactive prompt (print mode)
claude_continue.sh - Continue previous conversation

All scripts automatically use the configured Claude Code binary at /usr/lib/node_modules/@anthropic-ai/claude-code/cli.js.

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

MissingGITHUB OPENCLEW

Endpoints

Dossier API Snapshot API Contract API Trust API

Contract coverage

Status

missing

Auth

None

Streaming

Data region

Unspecified

Protocol support

MCP: self-declaredOpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.

Invocation examples

curl -s "https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/snapshot"

curl -s "https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/contract"

curl -s "https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.

No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media

No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors

GITLAB_AI_CATALOGgitlab-mcp

Rank

A Model Context Protocol (MCP) server for GitLab

Traction

No public download signal

Freshness

Updated 2d ago

MCP

GITLAB_PUBLIC_PROJECTSgitlab-mcp

Rank

A Model Context Protocol (MCP) server for GitLab

Traction

No public download signal

Freshness

Updated 2d ago

MCP

GITLAB_AI_CATALOGrmcp-openapi

Rank

Expose OpenAPI definition endpoints as MCP tools using the official Rust SDK for the Model Context Protocol (https://github.com/modelcontextprotocol/rust-sdk)

Traction

No public download signal

Freshness

Updated 2d ago

MCP

GITLAB_AI_CATALOGrmcp-actix-web

Rank

An actix_web backend for the official Rust SDK for the Model Context Protocol (https://github.com/modelcontextprotocol/rust-sdk)

Traction

No public download signal

Freshness

Updated 2d ago

MCP

Machine Appendix

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "MCP",
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-04-17T00:55:52.367Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "MCP",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "openai",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:MCP|unknown|profile protocol:OPENCLEW|unknown|profile capability:openai|supported|profile"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Hangoutlin Wq",
    "href": "https://github.com/hangoutlin-wq/openclaw-claude-code-skill",
    "sourceUrl": "https://github.com/hangoutlin-wq/openclaw-claude-code-skill",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-14T22:23:34.792Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "MCP, OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-04-14T22:23:34.792Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/hangoutlin-wq-openclaw-claude-code-skill/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]