CodexBar Live QA
steipete/CodexBar
Runs live QA for the CodexBar app: provider usage matrix checks through its packaged CLI, config validation and menu checks, with 1Password-backed credentials handled safely.
Runs real end-to-end tests for claude-tap against the actual Claude CLI, in a pytest mode and an interactive tmux mode, and checks the resulting traces.
Install Claude CLI Real E2E Tests
$ npx skills add liaohch3/claude-tap --skill real-e2e-test -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install liaohch3/claude-tap real-e2e-test --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/liaohch3/claude-tap.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/real-e2e-test .claude/skills/real-e2e-test && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "real-e2e-test" agent skill from https://github.com/liaohch3/claude-tap/tree/main/.agents/skills/real-e2e-test into .claude/skills/real-e2e-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "real-e2e-test", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/liaohch3/claude-tap/tree/main/.agents/skills/real-e2e-testType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add liaohch3/claude-tap --skill real-e2e-test -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install liaohch3/claude-tap real-e2e-test --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/liaohch3/claude-tap.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/real-e2e-test .agents/skills/real-e2e-test && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "real-e2e-test" agent skill from https://github.com/liaohch3/claude-tap/tree/main/.agents/skills/real-e2e-test into .agents/skills/real-e2e-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "real-e2e-test", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add liaohch3/claude-tap --skill real-e2e-test -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install liaohch3/claude-tap real-e2e-test --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/liaohch3/claude-tap.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/real-e2e-test .cursor/skills/real-e2e-test && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "real-e2e-test" agent skill from https://github.com/liaohch3/claude-tap/tree/main/.agents/skills/real-e2e-test into .cursor/skills/real-e2e-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "real-e2e-test", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/liaohch3/claude-tap.git --path .agents/skills/real-e2e-test--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add liaohch3/claude-tap --skill real-e2e-test -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install liaohch3/claude-tap real-e2e-test --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/liaohch3/claude-tap.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/real-e2e-test .gemini/skills/real-e2e-test && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "real-e2e-test" agent skill from https://github.com/liaohch3/claude-tap/tree/main/.agents/skills/real-e2e-test into .gemini/skills/real-e2e-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "real-e2e-test", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install liaohch3/claude-tap real-e2e-testInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add liaohch3/claude-tap --skill real-e2e-test -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/liaohch3/claude-tap.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/real-e2e-test .github/skills/real-e2e-test && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "real-e2e-test" agent skill from https://github.com/liaohch3/claude-tap/tree/main/.agents/skills/real-e2e-test into .github/skills/real-e2e-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "real-e2e-test", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add liaohch3/claude-tap --skill real-e2e-test -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install liaohch3/claude-tap real-e2e-test --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/liaohch3/claude-tap.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/real-e2e-test .opencode/skills/real-e2e-test && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "real-e2e-test" agent skill from https://github.com/liaohch3/claude-tap/tree/main/.agents/skills/real-e2e-test into .opencode/skills/real-e2e-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "real-e2e-test", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
real-e2e-test- GitHub stars
- 3.3k
- Token cost
- ~693 tokens
- SKILL.md length
- 269 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
Runs real end-to-end tests for claude-tap against the actual Claude CLI, in a pytest mode and an interactive tmux mode, and checks the resulting traces.
- Validating claude-tap end to end against a real Claude CLI session
- SKILL.md covers Prerequisites, Mode 1: Pytest Real E2E (7…, Mode 2: tmux Interactive Real… and Verification Checklist (for…, plus 2 more sections
- Calls uv and brew; needs SUBMIT_KEY
- Debugging a single real E2E test with verbose output
What it does
The tests start claude-tap from local source, connect to the real Claude CLI and verify the trace output. They need the claude CLI installed and authenticated, Python dev dependencies installed with uv sync --extra dev, and tmux for the interactive mode.
Mode one is a pytest suite of seven real E2E cases, run with uv run pytest tests/e2e/ and the --run-real-e2e flag, since these tests are skipped by default. A single test or debug output can be selected, and each case starts a fresh proxy server and trace directory. Cases cover single-turn and multi-turn capture, tool use, HTML viewer generation, API key redaction and streaming SSE capture.
Mode two uses scripts/run_real_e2e_tmux.sh to drive the Claude Code TUI interactively when non-print behavior must be validated, with prompts, submit key and other values overridable through environment variables. Both modes finish with a checklist: the newest trace file contains both prompts, at least two requests hit /v1/messages, one response has a tool_use block, and an HTML viewer file is generated. For portability, shell assertions use grep -F instead of rg.
When your agent uses it
- Validating claude-tap end to end against a real Claude CLI session
- Debugging a single real E2E test with verbose output
- Checking interactive Claude Code behavior inside tmux
Example prompts
- “Run the real E2E pytest suite for claude-tap and report any failures.”
- “Run only test_single_turn with debug output.”
- “Run the tmux real E2E script and check that both prompts appear in the latest trace.”
Requirements
- The claude CLI, installed and authenticated
- uv with the dev dependencies installed
- tmux, for the interactive mode
What it can do on your machine
Read from SKILL.md and the folder at commit 4cc867d. 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
Shell commands in SKILL.md call:
uvbrew
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
SUBMIT_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Claude CLI Real E2E Tests loads about 693 tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 269 words of instructions outside code blocks.
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
Auto-check passed
The automated check found no risky patterns in SKILL.md.
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); files beside SKILL.md are not scanned.
SKILL.md
The full file from liaohch3/claude-tap at commit 4cc867d, republished under its MIT licence (© liaohch3). 269 words, ~693 tokens.
Download SKILL.mdSave it as
.claude/skills/real-e2e-test/SKILL.md (or your agent's skills folder).- name
- real-e2e-test
- description
- Run real E2E tests against Claude CLI in pytest and tmux modes
- tags
- testing, e2e, integration, tmux
Real E2E Test Skill
Run real end-to-end tests that start claude-tap from local source, connect to the
real Claude CLI, and verify trace output.
Prerequisites
claudeCLI installed and authenticated- Python dev dependencies installed:
uv sync --extra dev tmuxinstalled for interactive mode (brew install tmux)
Mode 1: Pytest Real E2E (7 test cases)
Run all real E2E tests
uv run pytest tests/e2e/ --run-real-e2e --timeout=300 -vRun a single test
uv run pytest tests/e2e/test_real_proxy.py::TestRealProxy::test_single_turn --run-real-e2e --timeout=180 -v -sRun with debug output
uv run pytest tests/e2e/ --run-real-e2e --timeout=300 -v -s --tb=longMode 2: tmux Interactive Real E2E
Use this when you need to validate non--p interactive behavior in Claude Code TUI.
scripts/run_real_e2e_tmux.shOptional overrides:
PROMPT_ONE="Use the shell tool to run command ls in the current directory, then reply with any 5 filenames only." \
PROMPT_TWO="Thank you." \
SUBMIT_KEY="Enter" \
PERMISSION_MODE="bypassPermissions" \
scripts/run_real_e2e_tmux.shImportant tmux interaction notes:
- Submit key is
Enterfor Claude Code TUI in tmux (confirmed working). PROMPT_ONEshould intentionally trigger tool use.- For portability, use
grep -Finstead ofrgin shell assertions (rgmay be unavailable).
Verification Checklist (for both modes)
- Latest trace
.jsonlcontains both prompts (PROMPT_ONE,PROMPT_TWO) - At least 2 requests hit
/v1/messages - At least one response content block has
"type": "tool_use" - HTML viewer file is generated (
trace_*.html)
Notes
- Real E2E tests are skipped by default;
--run-real-e2eis required. - Each pytest case starts a fresh proxy server and trace directory.
- Timeouts are intentionally generous because real API calls are involved.
- tmux mode includes retry logic for prompt submission and post-run JSONL assertions.
Pytest Test Cases
| Test | Timeout | What It Tests |
|---|---|---|
test_single_turn | 180s | Basic prompt/response trace capture |
test_multi_turn | 300s | Conversation memory with -c flag |
test_tool_use | 180s | Tool use generates multiple trace records |
test_html_viewer_generated | 180s | HTML viewer generated with embedded trace data |
test_api_key_redaction | 180s | API keys redacted from trace output |
test_streaming_sse_capture | 180s | SSE events captured in streaming mode |
test_trace_summary | 180s | CLI stdout includes trace summary and API call count |
© liaohch3, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/real-e2e-test of liaohch3/claude-tap.
Open the folder on GitHubat commit 4cc867d
Compare with similar skills
Claude CLI Real E2E Tests next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Claude CLI Real E2E Tests this skillliaohch3/claude-tap | 3.3k | — | ~693 | Automated safety check: Pass | MIT | |
| CodexBar Live QAsteipete/CodexBar | 22k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Drive MiMo CodeXiaomiMiMo/MiMo-Code | 14k | — | ~3.9k | Automated safety check: Pass | MIT | |
| Senpi Agent QA Harnesscode-yeongyu/senpi | 470 | — | ~2.7k | Automated safety check: Notes | MIT | |
| tmux Real User TestingQwenLM/qwen-code | 28k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Verify Omnigent End-to-Endomnigent-ai/omnigent | 11k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Drive MiMo Code
XiaomiMiMo/MiMo-Code
Lets one MiMoCode process drive another, headless with JSON events or interactively through tmux, to test behavior and visual regressions with parseable evidence.
Senpi Agent QA Harness
code-yeongyu/senpi
Checks changes to the senpi coding agent by driving the real CLI from source in an isolated sandbox, over RPC, terminal UI, mock model and CLI smoke channels.
tmux Real User Testing
QwenLM/qwen-code
Drives Qwen Code in a real tmux session the way a user would and saves a readable step-by-step transcript of each screen for maintainers to review.
Verify Omnigent End-to-End
omnigent-ai/omnigent
Spins up an isolated Omnigent server, runner and mock model to prove a user-facing behavior or bug fix with recorded evidence instead of reasoning from code.
Designing Tests
CloudAI-X/claude-workflow-v2
Designs and implements testing strategies for any codebase. An agent skill from CloudAI-X/claude-workflow-v2.
More from liaohch3/claude-tap
All 11 skills in this repoCodex E2E Trace Validation
liaohch3/claude-tap
Runs a real Codex CLI session through claude-tap and produces trace evidence and viewer screenshots for pull requests that touch capture, proxying or the viewer.
Terminal Demo Video Recorder
liaohch3/claude-tap
Records a real tmux end-to-end run with asciinema, converts it to a GIF and MP4, and captures trace viewer screenshots with Playwright.
JS-in-HTML Testing
liaohch3/claude-tap
Tests JavaScript embedded in an HTML file in two layers: pytest checks of the logic ported to Python, and Playwright runs in a real browser for the DOM.
Maintainer Docs Legibility Check
liaohch3/claude-tap
Runs local checks on maintainer docs for stale review dates, missing manifest paths and plan state drift, matching what the CI workflow enforces.
Playwright Screen Recording
liaohch3/claude-tap
Records headless Playwright sessions as .webm videos to show a bug fix working or to give pull request reviewers visual evidence.
PR Preflight Check
liaohch3/claude-tap
Runs a single merge-readiness check on a pull request: metadata, GitHub Actions status, local lint, format and test gates, and PR body rules, ending in READY or NOT_READY.
Related
Categories
Questions about Claude CLI Real E2E Tests
What does Claude CLI Real E2E Tests do?
Runs real end-to-end tests for claude-tap against the actual Claude CLI, in a pytest mode and an interactive tmux mode, and checks the resulting traces. The tests start claude-tap from local source, connect to the real Claude CLI and verify the trace output. They need the claude CLI installed and authenticated, Python dev dependencies installed with uv sync --extra dev, and tmux for the interactive mode.
When should I use Claude CLI Real E2E Tests?
Claude CLI Real E2E Tests fits situations like: validating claude-tap end to end against a real Claude CLI session; debugging a single real E2E test with verbose output; checking interactive Claude Code behavior inside tmux.
How do I install Claude CLI Real E2E Tests in Claude Code?
Run `npx skills add liaohch3/claude-tap --skill real-e2e-test -a claude-code`. Or copy the skill folder (.agents/skills/real-e2e-test in liaohch3/claude-tap) into .claude/skills/real-e2e-test in your project. Claude Code loads it when a task matches its description.
How do I install Claude CLI Real E2E Tests in Codex?
Run `npx skills add liaohch3/claude-tap --skill real-e2e-test -a codex`. Or copy the skill folder (.agents/skills/real-e2e-test in liaohch3/claude-tap) into .agents/skills/real-e2e-test in your project. Codex loads it when a task matches its description.
Can I use Claude CLI Real E2E Tests in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add liaohch3/claude-tap --skill real-e2e-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/real-e2e-test, .gemini/skills/real-e2e-test, .github/skills/real-e2e-test and .opencode/skills/real-e2e-test in your project.
What does Claude CLI Real E2E Tests need to run?
Going by SKILL.md and its folder, Claude CLI Real E2E Tests needs the command-line tools its instructions call (uv and brew) and credentials named SUBMIT_KEY. Our summary lists: The claude CLI, installed and authenticated; uv with the dev dependencies installed; tmux, for the interactive mode.
Does Claude CLI Real E2E Tests access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Claude CLI Real E2E Tests safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Claude CLI Real E2E Tests use?
Claude CLI Real E2E Tests is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Claude CLI Real E2E Tests use?
About 693 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Claude CLI Real E2E Tests?
Skills that share tags, products or a category with Claude CLI Real E2E Tests: CodexBar Live QA (steipete/CodexBar, 22k stars), Drive MiMo Code (XiaomiMiMo/MiMo-Code, 14k stars), Senpi Agent QA Harness (code-yeongyu/senpi, 470 stars) and tmux Real User Testing (QwenLM/qwen-code, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Claude CLI Real E2E Tests?
liaohch3 (a GitHub user) maintains it in liaohch3/claude-tap, which has 3,267 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 22, 2026.
Source: liaohch3/claude-tap on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.