Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Use berth to work across development boxes — list repos (locations) and their worktrees, make a worktree or a task (a worktree with an agent in it), start or read terminal sessions, find which port…
Install Berth
$ npx skills add sean-brydon/berthd --skill berth -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sean-brydon/berthd berth --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/sean-brydon/berthd.git skills-src && mkdir -p .claude/skills && cp -r skills-src/internal/integrations/skills/berth .claude/skills/berth && 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 "berth" agent skill from https://github.com/sean-brydon/berthd/tree/main/internal/integrations/skills/berth into .claude/skills/berth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "berth", 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/sean-brydon/berthd/tree/main/internal/integrations/skills/berthType 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 sean-brydon/berthd --skill berth -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sean-brydon/berthd berth --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sean-brydon/berthd.git skills-src && mkdir -p .agents/skills && cp -r skills-src/internal/integrations/skills/berth .agents/skills/berth && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "berth" agent skill from https://github.com/sean-brydon/berthd/tree/main/internal/integrations/skills/berth into .agents/skills/berth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "berth", 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 sean-brydon/berthd --skill berth -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sean-brydon/berthd berth --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sean-brydon/berthd.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/internal/integrations/skills/berth .cursor/skills/berth && 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 "berth" agent skill from https://github.com/sean-brydon/berthd/tree/main/internal/integrations/skills/berth into .cursor/skills/berth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "berth", 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/sean-brydon/berthd.git --path internal/integrations/skills/berth--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 sean-brydon/berthd --skill berth -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sean-brydon/berthd berth --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sean-brydon/berthd.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/internal/integrations/skills/berth .gemini/skills/berth && 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 "berth" agent skill from https://github.com/sean-brydon/berthd/tree/main/internal/integrations/skills/berth into .gemini/skills/berth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "berth", 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 sean-brydon/berthd berthInstalls 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 sean-brydon/berthd --skill berth -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sean-brydon/berthd.git skills-src && mkdir -p .github/skills && cp -r skills-src/internal/integrations/skills/berth .github/skills/berth && 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 "berth" agent skill from https://github.com/sean-brydon/berthd/tree/main/internal/integrations/skills/berth into .github/skills/berth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "berth", 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 sean-brydon/berthd --skill berth -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sean-brydon/berthd berth --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sean-brydon/berthd.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/internal/integrations/skills/berth .opencode/skills/berth && 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 "berth" agent skill from https://github.com/sean-brydon/berthd/tree/main/internal/integrations/skills/berth into .opencode/skills/berth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "berth", 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
berth- GitHub stars
- 286
- Token cost
- ~1.7k tokens
- SKILL.md length
- 704 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use berth to work across development boxes — list repos (locations) and their worktrees, make a worktree or a task (a worktree with an agent in it), start or read terminal sessions, find which port…
- Asked to spin up a worktree
- SKILL.md covers Where am I?, Find your way around, Make work and A repository's config, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Check what runs where
What it does
Berth is an agent skill from sean-brydon/berthd. Use berth to work across development boxes — list repos (locations) and their worktrees, make a worktree or a task (a worktree with an agent in it), start or read terminal sessions, find which port and URL a worktree's dev server has, and read a repo's .berth/config.json (ports, env, services, hooks). Use when asked to spin up a worktree or agent on a box, check what runs where, find a dev server, or when you see BERTH variables in your environment. For driving other agents see berth-orchestrate; for showing a…
Its SKILL.md is about 1.7k 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 Development, covering Git worktrees. The repository describes itself as: Run coding agents on your dev boxes: worktrees, terminals, orchestration, kits and automations, with a desktop app. The licence is MIT.
When your agent uses it
- Asked to spin up a worktree
- Check what runs where
- Find a dev server
- You see BERTH variables in your environment
Example prompts
- “s dev server has, and read a repo”
- “/berth”
What it can do on your machine
Read from SKILL.md and the folder at commit fc5b184. 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 json).
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
Berth loads about 1.7k tokens when it runs. Until then it costs about 151 tokens; SKILL.md has 704 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 sean-brydon/berthd at commit fc5b184, republished under its MIT licence (© sean-brydon). 704 words, ~1,741 tokens.
Download SKILL.mdSave it as
.claude/skills/berth/SKILL.md (or your agent's skills folder).- name
- berth
- description
- Use berth to work across development boxes — list repos (locations) and their worktrees, make a worktree or a task (a worktree with an agent in it), start or read terminal sessions, find which port and URL a worktree's dev server has, and read a repo's .berth/config.json (ports, env, services, hooks). Use when asked to spin up a worktree or agent on a box, check what runs where, find a dev server, or when you see BERTH_* variables in your environment. For driving other agents see berth-orchestrate; for showing a page to the user see berth-preview; for automating with hooks see berth-hooks.
berth
berth connects a laptop to development boxes. Each box runs berthd; each
laptop runs berth. The commands are the same, with one difference:
- On a laptop, name the box first:
berth worktree new devl/shop/fix-login. - On a box, the box is implied:
berthd worktree new shop/fix-login.
command -v berth berthd tells you which you have. Add --json to any
listing and prefer it when you will parse the result. The examples below use
the box form (berthd …); on a laptop write berth … BOX/… instead.
Where am I?
When berth started your terminal, the environment says where you are:
| Variable | Meaning |
|---|---|
BERTH_BOX | the box's name |
BERTH_LOCATION | the repository (location) name, e.g. shop |
BERTH_ROOT_PATH | the repository's main checkout |
BERTH_WORKTREE_PATH, BERTH_WORKTREE_NAME | this worktree |
BERTH_WORKTREE_SLUG | shop_fix_login: safe for database and container names |
BERTH_BRANCH | the worktree's branch |
BERTH_PORT, BERTH_PORT_1, … | ports reserved for this worktree alone |
Use $BERTH_PORT for this worktree's dev server instead of a fixed port like
3000: every worktree has its own block, so two worktrees never collide, and
berth's URL for the worktree reaches whatever listens there.
Find your way around
berthd locations --json # repos and their worktrees (each with its first port)
berthd sessions --json # terminals and agents, with agent and agent_state
berthd services --json # which worktree each listening port belongs to
berthd ports --json # everything listening on the box
berthd agents # agent CLIs this box can startagent_state is idle (at its prompt), running, waiting (needs a human)
or finished (done with its turn).
Make work
# An agent beside you, in a split pane of the user's window:
berthd session new "$BERTH_LOCATION/$BERTH_WORKTREE_NAME" --agent claude --prompt "Review my diff" --open split
# A new worktree with an agent in it, in a new tab:
berthd task new shop/fix-login --agent claude --prompt "Fix the login redirect loop" --open tab
# A worktree alone, or any command in a terminal:
berthd worktree new shop/fix-login --base main
# A stacked branch, nested under the worktree it builds on:
berthd worktree new shop/fix-login-tests --base fix-login --parent fix-login
berthd session new shop/fix-login -- pnpm dev
# Read a terminal:
berthd session screen shop-fix-login-claude-1a2b --history 200- Start agents with
--agent ID --prompt TEXT(ids fromberthd agents), never-- claude "…": berth builds and quotes the command for that agent. --open split(beside the user's focused terminal) or--open tabshows it in the user's Shipyard app when they are looking at that worktree, and offers it otherwise. Use it whenever the user asks for an agent "beside me", "in a split" or "in a new tab".- A new agent may stop at a question before it is ready, such as "do you
trust this folder?". Wait with
berthd session wait NAME --for idle,waiting:idlemeans it is at its prompt;waitingmeans it needs the user, so tell them. Never poll the screen for a prompt. - An agent you start with
task newreports back to you: when its turn ends (or it needs a person) berth types a<berth-notification>into your session at your next idle. End your turn rather than waiting on it; see berth-orchestrate.
A branch that already exists, locally or on origin, is checked out as it is.
Session names are printed when they start and listed by sessions. Do not run
berthd session attach or berth attach yourself: they are interactive and
meant for humans.
Show full SKILL.md (303 more words)Show less
A repository's config
.berth/config.json in a repository (and the box's own config for that
location, which wins) says what every worktree gets:
{
"setup": "pnpm install",
"archive": "dropdb --if-exists $BERTH_WORKTREE_SLUG",
"ports": 2,
"env": { "DATABASE_URL": "postgres://localhost/$BERTH_WORKTREE_SLUG" },
"services": [{ "name": "web", "run": "pnpm dev --port $BERTH_PORT", "autostart": true }],
"hooks": [{ "on": "worktree.created", "run": "createdb $BERTH_WORKTREE_SLUG" }],
"agents": [{ "id": "claude", "name": "Claude Code", "command": "claude --model opus" }]
}berthd location config shop --json # the repo's, the box's, and the effective config
berthd service list shop/fix-login # this worktree's services and their state
berthd service start shop/fix-login web # also stop, restart
berthd service log shop/fix-login web # its output, when it will not stay upsetup runs after a worktree is created and archive before it is removed;
services start after setup and stop before archive. Edit the repository's
file only when the user asks you to change how every worktree is set up.
A box runs none of the repository's file (only its ports) until a person
trusts it on that box, and again after every change to it: location config
then shows repo_trust.state as untrusted or changed. Never trust it
yourself (--trust); tell the user what it wants to run and let them decide
in the app or with berth location config BOX/LOC --trust HASH.
Review links for the PRs you open
When you open a pull request, add its review link to the description so a teammate can open it on their own box in one click, set up by the team's kit:
Review it on your box: berth://review?repo=OWNER/NAME&pr=NThe link holds the repository and the PR number only; put nothing else in
it. In a review worktree, BERTH_REVIEW is the PR number: it is someone
else's work pinned to the commit they were shown, so don't push to its
branch.
Share publicly — only when a human asks
berthd share 3000 makes a port reachable by anyone on the internet
until berthd unshare <id>. Never share on your own initiative, and never
share anything with real data. Confirm with the user first and tell them the
URL and how to stop it.
When something fails
no paired box named X(laptop): runberth boxes; the name may differ.berthd serve is not running(box):berthd installstarts it.a "before:…" hook stopped …: the user's hooks refused the action. The message says why; do not try to work around it.
© sean-brydon, 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 internal/integrations/skills/berth of sean-brydon/berthd.
Open the folder on GitHubat commit fc5b184
Compare with similar skills
Berth 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 |
|---|---|---|---|---|---|---|
| Berth this skillsean-brydon/berthd | 286 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Migrate Core Code to Submodulestinyhumansai/openhuman | 42k | — | ~2.6k | Automated safety check: Pass | GPL-3.0 | |
| Finishing A Development Branchfarm-fe/farm | 5.6k | 34 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Git Worktree Cleanuplobehub/lobehub | 83k | — | ~2.8k | Automated safety check: Pass | Custom licence | |
| Keep Codex Fastvibeforge1111/keep-codex-fast | 1.6k | — | ~3.1k | Automated safety check: Pass | MIT |
Similar skills
Migrate Core Code to Submodules
tinyhumansai/openhuman
Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.
Finishing A Development Branch
farm-fe/farm
A skill your agent uses when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for…
Git Worktree Cleanup
lobehub/lobehub
Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.
Keep Codex Fast
vibeforge1111/keep-codex-fast
A skill your agent uses when Codex feels slow or bloated, when local sessions/logs/worktrees/config have grown over time, or when a user wants safe maintenance for Codex Desktop/CLI state.
Pre-Release PR Triage
jamiepine/voicebox
Sorts a backlog of open pull requests into must-merge, candidate, superseded and deferred, writes a triage doc and works the merge loop before a release.
More from sean-brydon/berthd
All 10 skills in this repoBerth Artifacts
sean-brydon/berthd
Show the user data as a chart, table, diagram, notes or one small page in their Shipyard app instead of a wall of text — write a berth.chart JSON, a CSV, Mermaid, Markdown or a self-contained HTML…
Berth Browser
sean-brydon/berthd
Use your worktree's own page in a headless browser on the box — open it, read a compact snapshot with @refs, click, fill, press keys, wait, take a screenshot to a file, read console errors, and set…
Berth Hooks
sean-brydon/berthd
Automate berth with hooks — run a command when something happens (an agent finishes or needs the user, a worktree is created or removed, a session starts) or gate an action with a before: hook that…
Berth Orchestrate
sean-brydon/berthd
Drive other coding agents through berth — prompt a running agent, wait for its turn to end, run a check in its worktree, loop until a check passes, hand work to a fresh agent in a new worktree, ask…
Berth Preview
sean-brydon/berthd
Run a worktree's dev server on its own port and show the page to the user in their Shipyard app — start the app on $BERTHPORT, check it answers, and open it as a browser tab next to your terminal…
Berth Visual Diff
sean-brydon/berthd
Check what your change did to a web app's pages before you say you're done — berthd shots compare screenshots your worktree's dev server and the main checkout's at phone, tablet and desktop widths…
Related
Categories
Questions about Berth
What does Berth do?
Use berth to work across development boxes — list repos (locations) and their worktrees, make a worktree or a task (a worktree with an agent in it), start or read terminal sessions, find which port…. Berth is an agent skill from sean-brydon/berthd.json (ports, env, services, hooks).
When should I use Berth?
Berth fits situations like: asked to spin up a worktree; check what runs where; find a dev server; you see BERTH variables in your environment.
How do I install Berth in Claude Code?
Run `npx skills add sean-brydon/berthd --skill berth -a claude-code`. Or copy the skill folder (internal/integrations/skills/berth in sean-brydon/berthd) into .claude/skills/berth in your project. Claude Code loads it when a task matches its description.
How do I install Berth in Codex?
Run `npx skills add sean-brydon/berthd --skill berth -a codex`. Or copy the skill folder (internal/integrations/skills/berth in sean-brydon/berthd) into .agents/skills/berth in your project. Codex loads it when a task matches its description.
Can I use Berth 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 sean-brydon/berthd --skill berth -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/berth, .gemini/skills/berth, .github/skills/berth and .opencode/skills/berth in your project.
What does Berth need to run?
SKILL.md names no scripts, command-line tools or credentials: Berth is instructions for the agent only.
Does Berth 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 Berth 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 Berth use?
Berth 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 Berth use?
About 1.7k tokens (SKILL.md is roughly 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 Berth?
Skills that share tags, products or a category with Berth: Finishing a Development Branch (obra/superpowers, 297k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars), Finishing A Development Branch (farm-fe/farm, 5.6k stars) and Git Worktree Cleanup (lobehub/lobehub, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Berth?
sean-brydon (a GitHub user) maintains it in sean-brydon/berthd, which has 286 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 9, 2026.
Source: sean-brydon/berthd on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.