Name: collaborating-with-claude-code
Author: ZhenHuangLab

Imported from ZhenHuangLab/collaborating-with-claude-code (SKILL.md). Install upstream with npx skills add ZhenHuangLab/collaborating-with-claude-code. Copyright stays with the author.

Collaborating with Claude Code

Use this skill for second opinions, code review, test design, or code implementations/alternatives. The bridge runs claude (Claude Code) non-interactively ("print" mode) and returns JSON.

The script is located at ~/.codex/skills/collaborating-with-claude-code/scripts/claude_code_bridge.py.

Timing

Claude Code often needs 1–2+ minutes per task.

Prefer running the bridge directly (no &); increase --timeout-s as needed (default: 1800s).
Do NOT redirect stdout to a file (e.g. > /tmp/out.json).
By default, the bridge streams Claude's assistant text to stderr, and prints only the final JSON envelope to stdout.

Context

Do NOT read the script unless you are modifying it;
Before running the script, ALWAYS use python <script_loc> --help to get the usage instructions.

Usage

please always require claude code to fully understand the codebase before responding or making any changes.
Put collaborating-with-claude-code terminal commands in the background terminal.
Always review claude code's responses (or changes it makes) and make sure they are correct, constructive and complete.
When claude code asks clarifying questions in a multi-turn session, always respond to its questions in that session based on current situation.

Default

full access (--full-access): use only in trusted repos/directories.
extended thinking ON (can disable via --no-extended-thinking).
step mode AUTO (can disable via --step-mode off).

Output format

The bridge prints JSON to stdout:

{"success": true, "SESSION_ID": "abc123", "agent_messages": "…Claude output…"}

Recommended delegation patterns

Guided coding: "Implement the code for [feature] following these specific steps/constraints."
Second opinion: "Propose an alternative approach and tradeoffs."
Code review: "Find bugs, race conditions, security issues; propose fixes."
Test design: "Write a test plan + edge cases; include example test code."
Diff review: "Review this patch; point out regressions and missing cases."

Install collaborating-with-claude-code and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "zhenhuanglab-collaborating-with-claude-code-collaboratin-69532d", "kind": "skill", "name": "collaborating-with-claude-code", "description": "Delegate code implementation/review/debugging/alternatives to Claude Code via a JSON bridge script. Multi-turn via SESSION_ID.", "publisher": "ZhenHuangLab", "version": "1.0.0", "capabilities": { "domains": [ "coding" ], "tags": [ "skill-md", "github" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Delegate code implementation/review/debugging/alternatives to Claude Code via a JSON bridge script. Multi-turn via SESSION_ID." ], "primary": false, "metadata": { "source": { "provider": "github", "repository": "https://github.com/ZhenHuangLab/collaborating-with-claude-code", "path": "SKILL.md", "ref": "83d04e3f4fc4f9cc4538fff253fd89ad23016f70", "url": "https://github.com/ZhenHuangLab/collaborating-with-claude-code/blob/83d04e3f4fc4f9cc4538fff253fd89ad23016f70/SKILL.md", "key": "ZhenHuangLab/collaborating-with-claude-code/SKILL.md" } }, "instructions": "# Collaborating with Claude Code\n\nUse this skill for second opinions, code review, test design, or code implementations/alternatives. The bridge runs `claude` (Claude Code) non-interactively (\"print\" mode) and returns JSON.\n\nThe script is located at `~/.codex/skills/collaborating-with-claude-code/scripts/claude_code_bridge.py`.\n\n## Timing\n\nClaude Code often needs **1–2+ minutes** per task.\n- Prefer running the bridge directly (no `&`); increase `--timeout-s` as needed (default: 1800s).\n- Do **NOT** redirect stdout to a file (e.g. `> /tmp/out.json`).\n- By default, the bridge streams Claude's as", "cost": { "context_tokens": 534 } }

collaborating-with-claude-code

About