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.
Establishes live repo truth at the start of a Codewhale session, five commands covering checkout, worktree sprawl, uncommitted changes and which AGENTS.md rules apply.
$ npx skills add codewhale-hq/Codewhale --skill cw-orient -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install codewhale-hq/Codewhale cw-orient --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/codewhale-hq/Codewhale.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/skills/cw-orient .claude/skills/cw-orient && 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 "cw-orient" agent skill from https://github.com/codewhale-hq/Codewhale/tree/main/docs/skills/cw-orient into .claude/skills/cw-orient/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cw-orient", 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/codewhale-hq/Codewhale/tree/main/docs/skills/cw-orientType 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 codewhale-hq/Codewhale --skill cw-orient -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install codewhale-hq/Codewhale cw-orient --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/codewhale-hq/Codewhale.git skills-src && mkdir -p .agents/skills && cp -r skills-src/docs/skills/cw-orient .agents/skills/cw-orient && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cw-orient" agent skill from https://github.com/codewhale-hq/Codewhale/tree/main/docs/skills/cw-orient into .agents/skills/cw-orient/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cw-orient", 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 codewhale-hq/Codewhale --skill cw-orient -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install codewhale-hq/Codewhale cw-orient --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/codewhale-hq/Codewhale.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/docs/skills/cw-orient .cursor/skills/cw-orient && 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 "cw-orient" agent skill from https://github.com/codewhale-hq/Codewhale/tree/main/docs/skills/cw-orient into .cursor/skills/cw-orient/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cw-orient", 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/codewhale-hq/Codewhale.git --path docs/skills/cw-orient--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 codewhale-hq/Codewhale --skill cw-orient -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install codewhale-hq/Codewhale cw-orient --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/codewhale-hq/Codewhale.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/docs/skills/cw-orient .gemini/skills/cw-orient && 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 "cw-orient" agent skill from https://github.com/codewhale-hq/Codewhale/tree/main/docs/skills/cw-orient into .gemini/skills/cw-orient/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cw-orient", 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 codewhale-hq/Codewhale cw-orientInstalls 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 codewhale-hq/Codewhale --skill cw-orient -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/codewhale-hq/Codewhale.git skills-src && mkdir -p .github/skills && cp -r skills-src/docs/skills/cw-orient .github/skills/cw-orient && 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 "cw-orient" agent skill from https://github.com/codewhale-hq/Codewhale/tree/main/docs/skills/cw-orient into .github/skills/cw-orient/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cw-orient", 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 codewhale-hq/Codewhale --skill cw-orient -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install codewhale-hq/Codewhale cw-orient --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/codewhale-hq/Codewhale.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/docs/skills/cw-orient .opencode/skills/cw-orient && 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 "cw-orient" agent skill from https://github.com/codewhale-hq/Codewhale/tree/main/docs/skills/cw-orient into .opencode/skills/cw-orient/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cw-orient", 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.
cw-orientEstablishes live repo truth at the start of a Codewhale session, five commands covering checkout, worktree sprawl, uncommitted changes and which AGENTS.md rules apply.
This skill is stage 1 of a six-stage loop and runs at the start or resumption of a session, or any time a handoff note, issue or plan claims the state of the repository, since that claim is treated as something to verify rather than trust. The repository runs many worktrees at once, and the skill frames editing the wrong one as the cheapest bug to avoid.
Five steps build that picture. Locating yourself checks the checkout root, branch, dirt and distance from the remote, treating a detached HEAD or a branch with no upstream as normal to note, not something to silently fix. Seeing the other lanes lists every worktree and recent branches, so an already-started piece of work is continued in its existing worktree instead of being duplicated in a new one. Reading the dirt before touching it means treating modified files you did not write as belonging to another agent or lane, left unstaged rather than stashed or checked out away.
A fourth step finds every AGENTS.md in the tree and applies the one nearest to the files about to be touched, since the nearest scoped file overrides the root one, and a fifth step establishes version truth from Cargo.toml and a version-check script rather than from memory.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 8d2fb45. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
gitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Codewhale Session Orientation loads about 1.1k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 561 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.
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.
The full file from codewhale-hq/Codewhale at commit 8d2fb45, republished under its MIT licence (© codewhale-hq). 561 words, ~1,115 tokens.
.claude/skills/cw-orient/SKILL.md (or your agent's skills folder).Open every session on live truth, not on a handoff note, a directory name, or what was true last time. This repo runs many worktrees at once; the cheapest bug to avoid is editing the wrong one. Five commands, then you know where you are.
This is stage 1 of the loop: orient → cw-slice → cw-gates → cw-dogfood → cw-land → cw-handoff.
Locate yourself. Checkout, branch, dirt, and how far you are from the remote:
git rev-parse --show-toplevel && git branch --show-current
git status --short --branch
git log --oneline --decorate -10A detached HEAD or a branch with no upstream is normal here — note it, don't "fix" it silently.
See the other lanes. Worktree sprawl is the standing hazard: several checkouts of this repo are usually live, each with its own dirty state.
git worktree list
git branch --sort=-committerdate --format='%(committerdate:short) %(refname:short)' | head -20If the work you were asked to do already has a checkout or worktree, use it. Do not start a second copy of the same lane, and do not create a worktree just because another agent is in this one — partition by file.
Read the dirt before you touch it. Modified files you did not write belong to someone else — another agent, another lane, an in-flight slice:
git status --porcelain
git diff --statPreserve them. Leave them unstaged, and do not git checkout -- or stash
another writer's work to get a clean tree. Only if your change genuinely
conflicts with that dirt is a fresh worktree warranted (cw-land).
Fix which guidance applies. The nearest scoped AGENTS.md wins over the
root one, and it is where the per-area rules actually live:
find . -name AGENTS.md -not -path './tmp/*' -not -path '*/node_modules/*' -not -path './target/*'Today: root AGENTS.md, crates/tui/AGENTS.md,
crates/localization/locales/AGENTS.md, web/AGENTS.md. Read the one that owns the
files you are about to touch.
Establish version truth from source, not memory.
grep -m1 '^version' Cargo.toml
./scripts/release/check-versions.shcheck-versions.sh is the drift gate across the workspace version, npm,
Cargo.lock, the changelog, and the README. If it disagrees with what you
were told, believe the script.
Only if the task is about the community queue — issues, PRs, harvesting,
credit — pull the live queue with the gh-* skills in this directory rather
than assuming from memory. When the task is local-only, stay offline and
record the missing external receipt instead.
.md file's confident prose. All three have been wrong here.git
describes reality.git checkout -- files you did not modify.
Worktree dirt is usually another writer, not garbage.main —
that lane is retirement material, not a base.AGENTS.md "probably covers it". The
scoped files carry the rules that actually get violated.Open with a short status block. Skip fields that are empty or normal — a
clean tree on main with no related worktrees is one line, not five:
check-versions.sh agrees;AGENTS.md files govern this change.© codewhale-hq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in docs/skills/cw-orient of codewhale-hq/Codewhale.
Open the folder on GitHubat commit 8d2fb45
Codewhale Session Orientation 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 |
|---|---|---|---|---|---|---|
| Codewhale Session Orientation this skillcodewhale-hq/Codewhale | 41k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Finishing A Development Branchfarm-fe/farm | 5.6k | 34 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Codebase Knowledge Graph Q&AEgonex-AI/Understand-Anything | 86k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Understand ExplainEgonex-AI/Understand-Anything | 86k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Git Worktree Cleanuplobehub/lobehub | 83k | — | ~2.8k | Automated safety check: Pass | Custom licence |
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.
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…
Egonex-AI/Understand-Anything
Answers questions about a codebase by searching a prebuilt knowledge graph of its files, functions, classes and dependencies, not by rereading every source file.
Egonex-AI/Understand-Anything
Gives an in-depth explanation of one file, function or module by reading the project's knowledge graph and checking that the graph is still fresh.
lobehub/lobehub
Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.
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.
codewhale-hq/Codewhale
Proves a Codewhale change in the real product: a stamped release build, an atomic local install, fresh-shell verification and manual QA that automated gates cannot cover.
codewhale-hq/Codewhale
Writes a paste-ready handoff for the next agent session, opening with a state-check command block and separating done, suspected and blocked work.
codewhale-hq/Codewhale
Decides how verified work should reach main, directly, in a worktree or on an integration branch, while keeping contributor credit and respecting merge gates.
codewhale-hq/Codewhale
Guides when and how to split multi-step coding, research or verification work into focused sub-agent runs while the parent keeps integration and final checks.
codewhale-hq/Codewhale
Triages and manages Codewhale fleet runs and workers with typed commands, classifying failures and choosing a safe restart, resume or escalation.
codewhale-hq/Codewhale
Moves a list of GitHub issues into a milestone or assigns them to owners with the gh CLI, checking each one before and after the change.
Works with
Categories
Establishes live repo truth at the start of a Codewhale session, five commands covering checkout, worktree sprawl, uncommitted changes and which AGENTS.md rules apply. This skill is stage 1 of a six-stage loop and runs at the start or resumption of a session, or any time a handoff note, issue or plan claims the state of the repository, since that claim is treated as something to verify rather than trust. The repository runs many worktrees at once, and the skill frames editing the wrong one as the cheapest bug to avoid.
Codewhale Session Orientation fits situations like: starting or resuming a Codewhale work session; taking over work from another agent or an earlier handoff note; checking whether a given checkout owns the files you are about to edit; finding out which worktrees and branches are currently live.
Run `npx skills add codewhale-hq/Codewhale --skill cw-orient -a claude-code`. Or copy the skill folder (docs/skills/cw-orient in codewhale-hq/Codewhale) into .claude/skills/cw-orient in your project. Claude Code loads it when a task matches its description.
Run `npx skills add codewhale-hq/Codewhale --skill cw-orient -a codex`. Or copy the skill folder (docs/skills/cw-orient in codewhale-hq/Codewhale) into .agents/skills/cw-orient in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add codewhale-hq/Codewhale --skill cw-orient -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cw-orient, .gemini/skills/cw-orient, .github/skills/cw-orient and .opencode/skills/cw-orient in your project.
Going by SKILL.md and its folder, Codewhale Session Orientation needs the command-line tools its instructions call (git). Our summary lists: A Codewhale checkout with git worktree support.
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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.
Codewhale Session Orientation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Codewhale Session Orientation: Finishing a Development Branch (obra/superpowers, 297k stars), Finishing A Development Branch (farm-fe/farm, 5.6k stars), Codebase Knowledge Graph Q&A (Egonex-AI/Understand-Anything, 86k stars) and Understand Explain (Egonex-AI/Understand-Anything, 86k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
codewhale-hq (a GitHub organization) maintains it in codewhale-hq/Codewhale, which has 41,078 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on October 9, 2026.
Source: codewhale-hq/Codewhale on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.