Agent Feature Reproduction

What it does

When your agent uses it

• Cloning a slash command or UI behavior from Codex into Qwen Code
• Capturing the request bodies and tool schemas another agent sends
• Recording a terminal-visible feature of Claude Code to match it elsewhere

Example prompts

• “Reproduce Claude Code's plan mode in this repo, using Claude Code as the reference agent.”
• “Capture what Codex sends to the model when I run its review command, then build the same in Qwen Code.”
• “Use codex as the reference and record the terminal output for the status feature.”

Requirements

• Codex or Claude Code installed locally as the reference agent
• tmux, for terminal capture
• Python and a MITM capture setup for the bundled scripts

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

1. 1Define the feature surface in one sentence: command, trigger, expected UI/output, and a minimal prompt that exercises it.
2. 2Select codex or claude-code as the reference agent and discover its local launch command.
3. 3Inspect the target repo enough to identify the likely module boundaries and Qwen Code launch command before changing code.
4. 4Run the nested reference agent against the feature with capture enabled
5. 5Extract behavioral facts from the trace
6. 6Implement the smallest compatible behavior in Qwen Code using its existing patterns.
7. 7Add focused tests or a reproducible smoke command.
8. 8Hand off to $agent-reproduce-align when implementation exists and parity needs iteration.

What it can do on your machine

Read from SKILL.md and the folder at commit d9c6f8c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 4 files in scripts/ (Python and Shell), which the agent can run.

  Shell commands in SKILL.md call:

  • claude
  • codex

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Feature Reproduction loads about 1.5k tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 74 tokens; SKILL.md has 595 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~74

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from QwenLM/qwen-code at commit d9c6f8c, republished under its Apache-2.0 licence (© QwenLM). 595 words, ~1,457 tokens.

name

agent-reproduce-feature

description

Use when reproducing an existing Codex or Claude Code feature in Qwen Code or another agent CLI by choosing a reference agent, capturing HTTP request bodies, prompts, tool/function schemas, terminal output, and then implementing the matching behavior in the target repo.

command -v codex || true
command -v claude || command -v claude-code || true

{
  "reference_agent": "codex",
  "reference_interactive_command": "codex",
  "reference_headless_command": "codex exec",
  "target_agent": "qwen-code",
  "target_repo": "."
}

mkdir -p .repro-runs/slash-command-baseline
.qwen/skills/agent-reproduce-feature/scripts/run_with_mitm.sh \
  .repro-runs/slash-command-baseline \
  -- codex exec "exercise the Codex feature here"

.qwen/skills/agent-reproduce-feature/scripts/run_tmux_capture.sh \
  .repro-runs/slash-command-claude \
  claude

.qwen/skills/agent-reproduce-feature/scripts/run_tmux_capture.sh \
  .repro-runs/slash-command-tui \
  codex

.qwen/skills/agent-reproduce-feature/scripts/capture_state.py \
  snapshot .repro-runs/slash-command-baseline/state-before \
  --agent codex

# Run the reference scenario here.

.qwen/skills/agent-reproduce-feature/scripts/capture_state.py \
  snapshot .repro-runs/slash-command-baseline/state-after \
  --agent codex

.qwen/skills/agent-reproduce-feature/scripts/capture_state.py \
  diff \
  .repro-runs/slash-command-baseline/state-before \
  .repro-runs/slash-command-baseline/state-after \
  --out-dir .repro-runs/slash-command-baseline/state-diff

© QwenLM, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references) in .qwen/skills/agent-reproduce-feature of QwenLM/qwen-code.

• SKILL.md
• references/capture-workflow.md
• scripts/capture_state.py
• scripts/llm_dump.py
• scripts/run_tmux_capture.sh
• scripts/run_with_mitm.sh

Open the folder on GitHubat commit d9c6f8c