Agent skill

Tau E2E Testing Tmux

by dpc in dpc/tau

Use Tau's dev tmux helper for manual agent-controlled end-to-end testing of the current checkout.

MPL-2.0Auto-check passedTesting & QA

Install Tau E2E Testing Tmux

skills CLI
$ npx skills add dpc/tau --skill tau-e2e-testing-tmux -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install dpc/tau tau-e2e-testing-tmux --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/dpc/tau.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/tau-e2e-testing-tmux .claude/skills/tau-e2e-testing-tmux && rm -rf skills-src

Use ~/.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/

Facts

Skill name
tau-e2e-testing-tmux
GitHub stars
104
Token cost
~659 tokens
SKILL.md length
269 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MPL-2.0

At a glance

Use Tau's dev tmux helper for manual agent-controlled end-to-end testing of the current checkout.

  • Works in 5 steps: Build the current checkout → Start an isolated tmux session. When… → Inspect the UI using the printed scratch… → …
  • Tasks that involve End-to-end testing
  • Calls cargo

What it does

Tau E2E Testing Tmux is an agent skill from dpc/tau. Use Tau's dev tmux helper for manual agent-controlled end-to-end testing of the current checkout.

Its SKILL.md is about 660 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering End-to-end testing. It works with tmux. The repository describes itself as: Tau Coding Agent - like Pi, but twice as much. The licence is MPL-2.0.

When your agent uses it

  • Tasks that involve End-to-end testing

Example prompts

  • “/tau-e2e-testing-tmux”

Workflow steps

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

  1. Build the current checkout
  2. Start an isolated tmux session. When --scratch-root / --root is omitted,
  3. Inspect the UI using the printed scratch root
  4. Send input
  5. Stop and clean up

What it can do on your machine

Read from SKILL.md and the folder at commit d2e1955. 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:

    • cargo

    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

Tau E2E Testing Tmux loads about 659 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 269 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~659

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 dpc/tau at commit d2e1955, republished under its MPL-2.0 licence (© dpc). 269 words, ~659 tokens.

Download SKILL.mdSave it as .claude/skills/tau-e2e-testing-tmux/SKILL.md (or your agent's skills folder).
name
tau-e2e-testing-tmux
description
Use Tau's dev tmux helper for manual agent-controlled end-to-end testing of the current checkout.

Tau end-to-end testing with tmux

Use the hidden tau dev tmux helper to run a manual Tau session in a private tmux server with isolated scratch state. This is for agent-controlled manual E2E checks, not an automated test framework.

  1. Build the current checkout:

    sh
    cargo build -p dpc-tau
  2. Start an isolated tmux session. When --scratch-root / --root is omitted, the helper generates a unique temporary scratch root and prints it in the startup output. Copy the printed scratch root: value into scratch_root for later commands:

    sh
    target/debug/tau dev tmux start \
      --tau-bin target/debug/tau
    scratch_root='<printed scratch root>'

    By default this sets scratch HOME, XDG_CONFIG_HOME, XDG_STATE_HOME, XDG_RUNTIME_DIR, disables all extensions, and enables only core-shell with its working directory pointed at scratch work/. Use --workdir only for an existing external directory that should not be created or chmodded by the helper.

    Provider access is opt-in. If ~/.config/tau/testing.yaml is absent, start prints a warning and copies no real provider credentials/config/state. To let the tmux Tau use selected real provider profiles, configure exact provider profile names:

    yaml
    testing_providers:
      - chatgpt

    Discover exact profile names in the real Tau environment with tau provider list; use the displayed profile name, which must match the stem of ~/.local/state/tau/auth.d/<provider>.json. The helper copies only ~/.local/state/tau/auth.d/<provider>.json for those names into scratch state and then enables provider-builtin; it never copies all providers or general user config. For more detail, load the built-in self-knowledge skills tau-self-knowledge-e2e-testing and tau-self-knowledge-ext-provider-builtin.

  3. Inspect the UI using the printed scratch root:

    sh
    target/debug/tau dev tmux capture --scratch-root "$scratch_root"
  4. Send input:

    sh
    target/debug/tau dev tmux send --scratch-root "$scratch_root" -- :version

    Add --no-enter to paste without submitting.

  5. Stop and clean up:

    sh
    target/debug/tau dev tmux stop --scratch-root "$scratch_root" --remove-scratch

Use --scratch-root or its shorter --root alias when you need a specific scratch location. Use --session, --width, and --height when you need a non-default session name or fixed pane size.

© dpc, MPL-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

Just SKILL.md in .agents/skills/tau-e2e-testing-tmux of dpc/tau.

Open the folder on GitHubat commit d2e1955

Compare with similar skills

Tau E2E Testing Tmux 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.

Tau E2E Testing Tmux compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tau E2E Testing Tmux this skilldpc/tau104—~659Automated safety check: PassMPL-2.0
CodexBar Live QAsteipete/CodexBar22k—~1.2kAutomated safety check: PassMIT
Drive MiMo CodeXiaomiMiMo/MiMo-Code14k—~3.9kAutomated safety check: PassMIT
Senpi Agent QA Harnesscode-yeongyu/senpi470—~2.7kAutomated safety check: NotesMIT
tmux Real User TestingQwenLM/qwen-code28k—~2.3kAutomated safety check: PassApache-2.0
Verify Omnigent End-to-Endomnigent-ai/omnigent11k—~1.6kAutomated safety check: PassApache-2.0

Similar skills

  • 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.

    22k GitHub stars~1.2k tokensUpdated today
    Testing & QAAuto-check passed
  • 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.

    14k GitHub stars~3.9k tokensUpdated 4 days ago
    Testing & QAAuto-check passed
  • 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.

    470 GitHub stars~2.7k tokensUpdated today
    Testing & QAAuto-check: notes
  • 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.

    28k GitHub stars~2.3k tokensUpdated today
    Testing & QAAuto-check passed
  • 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.

    11k GitHub stars~1.6k tokensUpdated today
    Testing & QAAuto-check passed
  • Con CLI E2E

    nowledge-co/con-terminal

    Validate Con's local socket control plane against a real running app session, and write/run con-test integration tests.

    625 GitHub stars~1.2k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • A skill your agent uses when selfci, Nix CI, coverage, cargo-crap, CRAP-score, crapAbsolute, or crapReport checks fail in Tau, or before changing the cargo-crap gates, thresholds, or flagged complex…

    104 GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed
  • A skill your agent uses when asked to "triage papercuts", review clanker-reported problems, or analyze and clear tau dev papercut reports.

    104 GitHub stars~2.4k tokensUpdated 2 days ago
    Auto-check passed
  • A skill your agent uses when asked to verify Tau harness tools or tool output behavior, especially read, edit, shell/shellcommand, line-oriented output, truncation, metadata headers, UTF-8 handling…

    104 GitHub stars~4.8k tokensUpdated 2 days ago
    Auto-check passed
  • A skill your agent uses when verifying Tau file and command tools: read, edit, replace, applypatch, shell, or shellcommand, including ranges, UTF-8, truncation, diffs, timeouts, mutation safety, and…

    104 GitHub stars~4k tokensUpdated 2 days ago
    Auto-check passed
  • A skill your agent uses when changing or reviewing Tau's static site under site/ and needing visual verification of layout, spacing, colors, alignment, desktop rendering, mobile rendering, or…

    104 GitHub stars~308 tokensUpdated 2 days ago
    Auto-check passed
  • A skill your agent uses when tracing or auditing Tau agent execution, including provider and cache cost, tool/background/wait latency, outer turns, compaction, delegated workflows, or performance…

    104 GitHub stars~658 tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Tau E2E Testing Tmux

What does Tau E2E Testing Tmux do?

Use Tau's dev tmux helper for manual agent-controlled end-to-end testing of the current checkout. Tau E2E Testing Tmux is an agent skill from dpc/tau. Use Tau's dev tmux helper for manual agent-controlled end-to-end testing of the current checkout.

When should I use Tau E2E Testing Tmux?

Tau E2E Testing Tmux fits situations like: tasks that involve End-to-end testing.

How do I install Tau E2E Testing Tmux in Claude Code?

Run `npx skills add dpc/tau --skill tau-e2e-testing-tmux -a claude-code`. Or copy the skill folder (.agents/skills/tau-e2e-testing-tmux in dpc/tau) into .claude/skills/tau-e2e-testing-tmux in your project. Claude Code loads it when a task matches its description.

How do I install Tau E2E Testing Tmux in Codex?

Run `npx skills add dpc/tau --skill tau-e2e-testing-tmux -a codex`. Or copy the skill folder (.agents/skills/tau-e2e-testing-tmux in dpc/tau) into .agents/skills/tau-e2e-testing-tmux in your project. Codex loads it when a task matches its description.

Can I use Tau E2E Testing Tmux 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 dpc/tau --skill tau-e2e-testing-tmux -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tau-e2e-testing-tmux, .gemini/skills/tau-e2e-testing-tmux, .github/skills/tau-e2e-testing-tmux and .opencode/skills/tau-e2e-testing-tmux in your project.

What does Tau E2E Testing Tmux need to run?

Going by SKILL.md and its folder, Tau E2E Testing Tmux needs the command-line tools its instructions call (cargo).

Does Tau E2E Testing Tmux access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Tau E2E Testing Tmux 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 Tau E2E Testing Tmux use?

Tau E2E Testing Tmux is published under the MPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tau E2E Testing Tmux use?

About 659 tokens (SKILL.md is roughly 2.6k 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 Tau E2E Testing Tmux?

Skills that share tags, products or a category with Tau E2E Testing Tmux: 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 Tau E2E Testing Tmux?

dpc (a GitHub user) maintains it in dpc/tau, which has 104 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 5, 2026.

Source: dpc/tau on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.