← Back to Skills Marketplace
0xmanel

Ask Claude

by 0xManel · GitHub ↗ · v1.1.1 · MIT-0
cross-platform ⚠ suspicious
323
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install ask-claude
Description
Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no...
README (SKILL.md)

Ask Claude — Execute & Report (with persistent sessions)

How to Run

ALWAYS use the synchronous shell tool — NEVER the process/background tool.

The command takes 30–120 seconds. Wait for it. Do NOT launch it as a background process.

The Two Modes

New session (default)

Use when starting a fresh task or new topic.

OUTPUT=$(/home/xmanel/.openclaw/workspace/run-claude.sh "prompt" "/workdir")
echo "$OUTPUT"

Continue session (--continue)

Use when the user is following up on a previous Claude task in the same workdir. Claude Code will have full memory of what was done before — files read, edits made, context gathered.

OUTPUT=$(/home/xmanel/.openclaw/workspace/run-claude.sh --continue "prompt" "/workdir")
echo "$OUTPUT"

When to use --continue

Use --continue when the user says things like:

  • "agora corrige o que encontraste"
  • "continua"
  • "e o ficheiro X?"
  • "faz o mesmo para..."
  • "e agora?"
  • "ok, e o erro de..."
  • Anything that clearly references what Claude just did

Use a new session when:

  • New unrelated task
  • User says "começa do zero" / "new task" / "esquece o anterior"
  • Different workdir/project

Session storage

Claude Code stores sessions per-directory in ~/.claude/projects/. As long as you use the same workdir, --continue picks up exactly where it left off — same file context, same conversation history, same edits.

Direct command (alternative to wrapper)

# New session
OUTPUT=$(cd /workdir && env -u CLAUDECODE claude --permission-mode bypassPermissions --print "task" 2>&1)

# Continue session
OUTPUT=$(cd /workdir && env -u CLAUDECODE claude --permission-mode bypassPermissions --print --continue "task" 2>&1)

Security & Privacy

Workspace-Only Access (User-Controlled): The skill operates exclusively on files inside the WORKDIR you specify. You have full control over what gets exposed:

  • /home/xmanel/.openclaw/workspace - General scripts
  • /home/xmanel/.openclaw/workspace/hyperliquid - Trading data
  • Any other directory of your choosing

What it DOES NOT do: The skill works exclusively on files inside the specified WORKDIR. You control what workdir to use:

  • /home/xmanel/.openclaw/workspace - General scripts
  • /home/xmanel/.openclaw/workspace/hyperliquid - Trading
  • Any other directory you specify

What it DOES NOT do:

  • ❌ Never access ~/.ssh, ~/.aws, ~/.config without explicit workdir
  • ❌ Never send data to external servers
  • ❌ Never store credentials or API keys

What it DOES:

  • 🔄 Runs claude CLI on files YOU choose
  • 📁 Indexes files only within YOUR workdir
  • 🎯 Returns output via chat (not stored remotely)

Technical Note: Uses --permission-mode bypassPermissions for technical reasons but does NOT require sudo/root access.


Common workdirs

Context Workdir
General/scripts /home/xmanel/.openclaw/workspace
Trading /home/xmanel/.openclaw/workspace/hyperliquid

After receiving output

  • Summarize in 1-3 lines what Claude did/found
  • Mention files created or edited
  • If error: analyze and suggest fix
  • If output is long: summarize, offer full output on request
Context Workdir
General/scripts /home/xmanel/.openclaw/workspace
Trading /home/xmanel/.openclaw/workspace/hyperliquid

After receiving output

  • Summarize in 1-3 lines what Claude did/found
  • Mention files created or edited
  • If error: analyze and suggest fix
  • If output is long: summarize, offer full output on request
Usage Guidance
Do not install blindly. Before using: (1) inspect the run-claude.sh wrapper and the 'claude' binary (origin, version, what network calls it makes); (2) test in an isolated sandbox or container; (3) avoid pointing the workdir at any sensitive files (SSH keys, AWS creds, ~/.config); (4) ask the author why --permission-mode bypassPermissions is required and remove it if unnecessary; (5) if you must use it, create a disposable user/home or ephemeral VM to limit persistent session storage in ~/.claude/projects/.
Capability Analysis
Type: OpenClaw Skill Name: ask-claude Version: 1.1.1 The skill contains hardcoded absolute paths to a specific user's home directory (/home/xmanel/) and references an external script (run-claude.sh) that is not included in the bundle. It explicitly instructs the agent to use the '--permission-mode bypassPermissions' flag, which disables Claude Code's built-in safety prompts, allowing for unmonitored file system and command execution. While these features facilitate automation, the combination of hardcoded user environments and bypassed security controls poses a significant risk of unauthorized actions.
Capability Assessment
Purpose & Capability
Name/description match the declared requirement for a 'claude' binary. However the SKILL.md is tightly tied to a specific user's paths (/home/xmanel/...) and references a wrapper script run-claude.sh that is not provided, which reduces portability and raises questions about what that script does.
Instruction Scope
Instructions assert 'workspace-only' operation but also state sessions are stored in ~/.claude/projects/ (outside the chosen workdir). The direct commands use --permission-mode bypassPermissions and unset CLAUDECODE, both of which change runtime behavior and could allow broader file/network access. The skill also claims 'never send data to external servers' despite invoking an external CLI that typically communicates with a service; that claim is not enforceable from the instructions alone.
Install Mechanism
Instruction-only skill with no install spec or downloaded artifacts—this lowers installation risk. The main risk is what the required 'claude' binary and the referenced run-claude.sh wrapper actually do, which are not included.
Credentials
No environment variables are declared, yet the SKILL.md manipulates the environment (env -u CLAUDECODE) and relies on a CLI that likely reads credentials/config from ~/.config or env vars. The skill explicitly promises not to touch ~/.ssh, ~/.aws, or ~/.config, but the CLI or session storage could still read those locations unless you verify otherwise.
Persistence & Privilege
Skill supports persistent sessions stored in ~/.claude/projects/, which persists conversation state outside the specified workdir and could retain data across runs. The use of --permission-mode bypassPermissions suggests the CLI may operate with relaxed permission checks, increasing blast radius if the wrapper or CLI are compromised.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ask-claude
  3. After installation, invoke the skill by name or use /ask-claude
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.1
- Improved wording in the Security & Privacy section for clarity around user control of workspace access - Reordered and clarified explanations to reduce redundancy in how workdirs are documented - No changes to functionality; documentation only
v1.1.0
Updated security documentation to clarify workspace-only access. File access scope now explicitly documented. Permission bypass is technical requirement, not security risk.
v1.0.0
- Initial release of the "ask-claude" skill. - Enables delegation of coding and file tasks to Claude Code CLI, with immediate result reporting in chat. - Supports persistent, context-aware sessions per workspace for ongoing tasks. - Safe and confined execution: no external data transfer, workspace-only file access. - Clear guidance on starting new sessions vs. continuing previous ones. - Provides output summaries, highlights file changes, and suggests fixes for errors.
Metadata
Slug ask-claude
Version 1.1.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is Ask Claude?

Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no... It is an AI Agent Skill for Claude Code / OpenClaw, with 323 downloads so far.

How do I install Ask Claude?

Run "/install ask-claude" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Ask Claude free?

Yes, Ask Claude is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Ask Claude support?

Ask Claude is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Ask Claude?

It is built and maintained by 0xManel (@0xmanel); the current version is v1.1.1.

💬 Comments