Agent skill

Herdr Throwaway Reproduction

by herdrdev in herdrdev/herdr

Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session.

Apache-2.0Auto-check passedDevelopment

Install Herdr Throwaway Reproduction

skills CLI
$ npx skills add herdrdev/herdr --skill herdr-throwaway-repro -a claude-code

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

GitHub CLI
$ gh skill install herdrdev/herdr herdr-throwaway-repro --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/herdrdev/herdr.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/herdr-throwaway-repro .claude/skills/herdr-throwaway-repro && 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
herdr-throwaway-repro
GitHub stars
43k
Token cost
~2.4k tokens
SKILL.md length
1,300 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
Apache-2.0

At a glance

Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session.

  • Works in 7 steps: Reject pending prompts and stop test… → Verify that harmless probe files or… → Stop the temporary named session with… → …
  • Reproducing a Herdr pane or terminal bug in isolation
  • SKILL.md covers Non-negotiable safety, Learn the installed interface…, Create the outer pane and Start the disposable session, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

A throwaway Herdr session is useful when a reproduction needs a real Herdr server, panes, PTYs, agents or the socket API without risking your main session. The agent opens a new outer pane next to the current one, starts a short, unique named session there, and drives the reproduction from the parent session through the CLI and API, using the nested TUI only to keep the session attached and supply terminal size.

Safety rules are strict: never run in the default session, never stop, restart, delete or kill the main server, never use pkill or guessed process IDs, never reuse or delete an unrelated named session, close only the pane it created and read every ID from command output instead of constructing it. Reproduction directories go in /var/tmp, destructive agent actions are not approved, and paid agent tokens are not spent without your say-so.

Because the installed binary is the authority, the agent first confirms it is inside Herdr and reads the relevant help for the installed version, avoiding bare herdr, which would launch the TUI, and noting which binary and version is being tested.

When your agent uses it

  • Reproducing a Herdr pane or terminal bug in isolation
  • Testing Herdr's socket API or persistence without risking the default session
  • Verifying agent behavior inside a disposable Herdr runtime

Example prompts

  • “Reproduce the pane resize bug in a throwaway Herdr session and report what happens.”
  • “Use a disposable named session to test whether persistence survives a restart.”
  • “Spin up a throwaway Herdr session and run a low-cost agent in it to check the API output.”

Requirements

  • An existing Herdr session to run from
  • The herdr CLI

Workflow steps

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

  1. Reject pending prompts and stop test applications cleanly when practical.
  2. Verify that harmless probe files or other test artifacts do not exist, or remove only artifacts created by this reproduction.
  3. Stop the temporary named session with the installed session command.
  4. Delete that same stopped session.
  5. Confirm it no longer appears as running.
  6. Wait for the outer pane to return to its shell.
  7. Close only the outer pane created by this workflow.

What it can do on your machine

Read from SKILL.md and the folder at commit 2563803. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and toml).

    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

Herdr Throwaway Reproduction loads about 2.4k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 1,300 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

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 herdrdev/herdr at commit 2563803, republished under its Apache-2.0 licence (© herdrdev). 1,300 words, ~2,417 tokens.

Download SKILL.mdSave it as .claude/skills/herdr-throwaway-repro/SKILL.md (or your agent's skills folder).
name
herdr-throwaway-repro
description
Create and control a disposable named Herdr session from inside an existing Herdr session. Use for isolated Herdr runtime, pane, terminal, process, API, persistence, or agent reproductions that should be driven through the CLI/API without touching the default session.

Herdr throwaway reproduction

Use a disposable named Herdr session when a reproduction needs a real Herdr server, panes, PTYs, agents, or socket API without risking the user's main session.

The temporary TUI only keeps the disposable session attached and supplies terminal geometry. Drive the reproduction from the parent session through Herdr's CLI/API. Do not manually operate the nested TUI unless the bug specifically requires client input.

Non-negotiable safety

  • Never run the reproduction in the default session.
  • Never stop, restart, delete, or kill the main Herdr server.
  • Never use pkill, broad process matching, or guessed PIDs for cleanup.
  • Create a unique session name. Never reuse or delete an unrelated named session.
  • Create a new outer pane and close only that pane during cleanup.
  • Read workspace, tab, pane, terminal, and agent IDs from command output. Never construct them.
  • Use /var/tmp for reproduction directories and potentially large artifacts.
  • Do not approve destructive or unnecessary agent actions.
  • Do not spend paid agent tokens without the user's approval. Use the requested low-cost model and the smallest useful prompts.

Learn the installed interface first

The installed binary is the authority. CLI syntax may have changed since this skill was written.

Confirm the caller is inside Herdr and inspect the relevant help before doing anything:

bash
test "${HERDR_ENV:-}" = 1
herdr --version
herdr --help
herdr session
herdr pane
herdr agent

Inspect nested command help before using unfamiliar or potentially mutating commands. Do not run bare herdr for discovery because it launches or attaches the TUI.

Record which Herdr binary and version the reproduction tests. If testing a checkout build, follow the repository's instructions for running that build instead of silently substituting the installed binary.

Create the outer pane

Create a sibling shell pane in the current tab without moving focus. Use an available Herdr layout tool when the harness provides one. Otherwise use the installed pane split command after checking its help.

Use /var/tmp or a dedicated reproduction directory as the new pane's cwd. Save the returned outer pane ID. This is the only parent-session pane that cleanup may close.

Start the disposable session

Choose a short unique name such as repro-<topic>-<timestamp>.

Before launching, explicitly allow nesting in the configuration the disposable client will actually load. HERDR_ENV=1 is inherited from the outer pane, so the launch is otherwise rejected unless [experimental].allow_nested is enabled. An isolated XDG_CONFIG_HOME does not inherit this setting from the user's global config, even when nesting is enabled there.

Create a test-only config under the reproduction directory using the file-writing tool. For a default-config reproduction, its contents can be:

toml
[experimental]
allow_nested = true

If reproducing with the user's configuration, copy that configuration into the test directory and enable allow_nested in its existing [experimental] table (or add the table if absent). Do not create duplicate tables or keys. Never edit the user's global configuration to permit a reproduction, and do not unset HERDR_ENV to bypass the nesting check.

Pass the absolute test config path as HERDR_CONFIG_PATH when launching below. Use the same override for config validation and any commands that must load the test config. This override selects a config file; it does not isolate the saved machine catalog or other global state. Use test-only XDG_CONFIG_HOME and XDG_STATE_HOME as well when the reproduction changes saved machines, and retain those overrides on every command addressing that test environment.

Run the named session inside the new outer pane. Clear inherited session selection, socket overrides, and caller IDs so the nested runtime cannot accidentally address the parent session:

bash
env \
  -u HERDR_SOCKET_PATH \
  -u HERDR_CLIENT_SOCKET_PATH \
  -u HERDR_SESSION \
  -u HERDR_WORKSPACE_ID \
  -u HERDR_TAB_ID \
  -u HERDR_PANE_ID \
  HERDR_CONFIG_PATH=<absolute-test-config-path> \
  herdr --session <session-name>

Add reproduction-specific environment variables to this launch command when needed. Environment variables that configure the server must be present before the named server starts.

Validate the test config with herdr config check using the same config override before launch. After launch, read the outer pane to catch startup errors such as nested herdr is disabled by default; do not assume the launch succeeded merely because pane run returned successfully.

Do not continue until the named session's API is ready. Confirm readiness by addressing that session from the parent and listing its panes.

Address only the disposable session

Every control command issued from the parent must clear inherited socket overrides and explicitly select the temporary session:

bash
env \
  -u HERDR_SOCKET_PATH \
  -u HERDR_CLIENT_SOCKET_PATH \
  -u HERDR_WORKSPACE_ID \
  -u HERDR_TAB_ID \
  -u HERDR_PANE_ID \
  HERDR_SESSION=<session-name> \
  herdr pane list

Repeat this prefix for every command. Do not rely on shell state persisting between tool calls.

Read the disposable root pane ID from pane list. Confirm its cwd and foreground process before starting anything in it.

Named sessions isolate runtime state, sockets, panes, and persistence. They still share global Herdr configuration and agent manifest overrides by default. Check configuration provenance when it could affect the reproduction. Do not modify shared configuration merely to make the test pass.

Show full SKILL.md (547 more words)Show less

Drive the reproduction through the API

Use pane commands for shells and ordinary processes:

  • pane run to start a command at an available shell prompt.
  • pane wait-output to wait for deterministic output.
  • pane read to capture terminal contents.
  • pane send-text for literal input.
  • pane send-keys for supported keys.
  • pane get, pane process-info, and pane layout for runtime state.

Use agent commands only after Herdr recognizes a coding agent:

  • agent start to launch a supported agent in an existing shell pane.
  • agent prompt to submit one prompt atomically.
  • agent wait to wait for working, blocked, idle, done, or unknown.
  • agent read to capture the agent terminal.
  • agent get and agent explain to inspect state and detection.
  • agent send-keys for interactive responses.

Run the relevant command group's help first because names and options may change.

Prefer waits over arbitrary sleeps. When timing itself is under test, record timestamps and use bounded polling. Capture state before, during, and after the transition being reproduced.

When a needed terminal key is unsupported by the high-level command, send its terminal sequence through the disposable pane only after confirming the target application's expected key. Never send raw control sequences to the parent pane.

Start agents carefully

Before launching an agent, inspect its installed --version and --help. Pass native agent arguments after Herdr's argument separator.

Use the exact model requested or approved by the user. Verify the model from the live agent screen instead of trusting an alias. Prefer low effort, safe mode, and manual permissions for a baseline when the agent supports them. Repeat with the user's real configuration only when the suspected behavior depends on hooks, plugins, or settings.

Use harmless operations for permission-state testing. Reject the pending action after evidence is captured and verify that no artifact was created.

Collect useful evidence

Record enough information for another person to repeat the result:

  • Herdr binary and version.
  • Named session and launch environment.
  • Target application or agent version and arguments.
  • Exact commands or prompts.
  • Pane and agent state before and after each transition.
  • Relevant pane read, agent read, agent explain, API output, and session logs.
  • Whether global config or a local manifest override was active.

Read the named session directory and socket from herdr session list instead of assuming their paths. Keep large evidence under /var/tmp unless the user asks to preserve it elsewhere.

Distinguish observed facts from proposed causes. First reproduce stock behavior, then change one variable at a time.

Cleanup

Cleanup is part of the reproduction, including after failure.

  1. Reject pending prompts and stop test applications cleanly when practical.
  2. Verify that harmless probe files or other test artifacts do not exist, or remove only artifacts created by this reproduction.
  3. Stop the temporary named session with the installed session command.
  4. Delete that same stopped session.
  5. Confirm it no longer appears as running.
  6. Wait for the outer pane to return to its shell.
  7. Close only the outer pane created by this workflow.

Never delete another named session because it looks stale. Never close the pane running the current agent or any pane not created for the reproduction.

Report the result

State what reproduced, what did not, and the exact transition that failed. Include cleanup status. Mention shared configuration or manifest overrides that may have influenced the result.

© herdrdev, 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

Just SKILL.md in .agents/skills/herdr-throwaway-repro of herdrdev/herdr.

Open the folder on GitHubat commit 2563803

Compare with similar skills

Herdr Throwaway Reproduction 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.

Herdr Throwaway Reproduction compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Herdr Throwaway Reproduction this skillherdrdev/herdr43k—~2.4kAutomated safety check: PassApache-2.0
Trellis Session Insightmindfold-ai/Trellis15k4 repos~1.7kAutomated safety check: PassAGPL-3.0
Native Data FetchingCherryHQ/cherry-studio-app4k6 repos~2.9kAutomated safety check: NotesMIT
Debugging Executionsn8n-io/n8n207k—~2.6kAutomated safety check: PassCustom licence
Aoti Debugpytorch/pytorch104k1 repos~1.7kAutomated safety check: PassCustom licence
Systematic Debuggingultralisp/ultralisp25851 repos~2.4kAutomated safety check: PassNone

Similar skills

  • Trellis Session Insight

    mindfold-ai/Trellis

    Reach into past AI conversation history through the trellis mem CLI.

    15k GitHub starsUsed in 4 repos~1.7k tokens
    DevelopmentAuto-check passed
  • Native Data Fetching

    CherryHQ/cherry-studio-app

    A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.

    4k GitHub starsUsed in 6 repos~2.9k tokens
    DevelopmentAuto-check: notes
  • Official

    Debug failed or wrong-output workflow executions using executions tools.

    207k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Aoti Debug

    pytorch/pytorch

    Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.

    104k GitHub starsUsed in 1 repo~1.7k tokens
    DevelopmentAuto-check passed
  • Systematic Debugging

    ultralisp/ultralisp

    A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    258 GitHub starsUsed in 51 repos~2.4k tokens
    DevelopmentAuto-check passed
  • Decides whether an OpenLogi device problem on macOS is a privacy-permission (TCC) problem, using agent log lines, and says which identity needs which grant.

    23k GitHub stars~2.5k tokensUpdated today
    DevelopmentAuto-check: notes

More from herdrdev/herdr

  • Audit herdr release readiness by comparing commits since the base release against next-release changelog and docs. Use when asked to run or apply the repo's…

    43k GitHub stars~289 tokensUpdated yesterday
    Auto-check passed
  • Herdr Issue Triage

    herdrdev/herdr

    Triages open herdr GitHub issues into a short decision-first Markdown table with a priority light, recommendation, age, reactions and a reason for each.

    43k GitHub stars~517 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Herdr Throwaway Reproduction

What does Herdr Throwaway Reproduction do?

Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session. A throwaway Herdr session is useful when a reproduction needs a real Herdr server, panes, PTYs, agents or the socket API without risking your main session. The agent opens a new outer pane next to the current one, starts a short, unique named session there, and drives the reproduction from the parent session through the CLI and API, using the nested TUI only to keep the session attached and supply terminal size.

When should I use Herdr Throwaway Reproduction?

Herdr Throwaway Reproduction fits situations like: reproducing a Herdr pane or terminal bug in isolation; testing Herdr's socket API or persistence without risking the default session; verifying agent behavior inside a disposable Herdr runtime.

How do I install Herdr Throwaway Reproduction in Claude Code?

Run `npx skills add herdrdev/herdr --skill herdr-throwaway-repro -a claude-code`. Or copy the skill folder (.agents/skills/herdr-throwaway-repro in herdrdev/herdr) into .claude/skills/herdr-throwaway-repro in your project. Claude Code loads it when a task matches its description.

How do I install Herdr Throwaway Reproduction in Codex?

Run `npx skills add herdrdev/herdr --skill herdr-throwaway-repro -a codex`. Or copy the skill folder (.agents/skills/herdr-throwaway-repro in herdrdev/herdr) into .agents/skills/herdr-throwaway-repro in your project. Codex loads it when a task matches its description.

Can I use Herdr Throwaway Reproduction 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 herdrdev/herdr --skill herdr-throwaway-repro -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/herdr-throwaway-repro, .gemini/skills/herdr-throwaway-repro, .github/skills/herdr-throwaway-repro and .opencode/skills/herdr-throwaway-repro in your project.

What does Herdr Throwaway Reproduction need to run?

SKILL.md names no scripts, command-line tools or credentials: Herdr Throwaway Reproduction is instructions for the agent only. Our summary lists: An existing Herdr session to run from; The herdr CLI.

Does Herdr Throwaway Reproduction 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 Herdr Throwaway Reproduction 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 Herdr Throwaway Reproduction use?

Herdr Throwaway Reproduction is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Herdr Throwaway Reproduction use?

About 2.4k tokens (SKILL.md is roughly 9.7k 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 Herdr Throwaway Reproduction?

Skills that share tags, products or a category with Herdr Throwaway Reproduction: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Debugging Executions (n8n-io/n8n, 207k stars) and Aoti Debug (pytorch/pytorch, 104k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Herdr Throwaway Reproduction?

herdrdev (a GitHub organization) maintains it in herdrdev/herdr, which has 43,015 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 8, 2026.

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