Agent skill

Codewhale Contributor Onboarding

by codewhale-hq in codewhale-hq/Codewhale

Reports whether a fresh Codewhale checkout is current, builds and passes its tests, and what changed since the contributor was last here, without touching the working tree.

MITAuto-check passedDevelopment

Install Codewhale Contributor Onboarding

skills CLI
$ npx skills add codewhale-hq/Codewhale --skill contributor-onboarding -a claude-code

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

GitHub CLI
$ gh skill install codewhale-hq/Codewhale contributor-onboarding --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/codewhale-hq/Codewhale.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/skills/contributor-onboarding .claude/skills/contributor-onboarding && 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
contributor-onboarding
GitHub stars
41k
Token cost
~1.3k tokens
SKILL.md length
658 words
Files
1
Skills in repo
63
Repo updated
First seen
Licence
MIT

At a glance

Reports whether a fresh Codewhale checkout is current, builds and passes its tests, and what changed since the contributor was last here, without touching the working tree.

  • Works in 6 steps: Inspect (read-only, always safe) → Sync — propose, never perform → Build → …
  • Getting oriented right after cloning the Codewhale repository
  • SKILL.md covers Invocation, Non-goals, Workflow and Reporting, plus 1 more section
  • Calls git and cargo

What it does

This skill answers four questions for someone who just cloned the repository: am I current, does it build, does it pass, and what changed while I was away, without a wall of prose and without any step touching the working tree on its own initiative. Loading the skill is explicitly not authority to fetch, pull, rebase, push or write files; every network or mutating step is a separate action the contributor must ask for after reading the plan, and a dirty tree is never stashed, discarded, reset or committed.

The workflow starts with read-only inspection: the current branch, whether the tree is clean or has dirty entries, and how far ahead or behind origin/main the branch is, reporting unavailable rather than guessing zero when origin/main has never been fetched. If the branch is behind, the skill prints the exact fetch and rebase or merge commands and stops rather than running them; if the tree is dirty, it proposes a recovery plan first, such as stashing, committing to a branch, or simply staying behind, and lets the contributor choose.

Only after that does it build the CLI binary in release mode, reporting the exit status and first error on failure without proceeding further, and then run the repository's exact verification gate. The skill never calls a model provider itself: the digest it produces comes from files and git output, not generated prose, and it does not claim a gate passed that it did not actually run.

When your agent uses it

  • Getting oriented right after cloning the Codewhale repository
  • Checking whether a checkout is behind main and what changed since it was last synced
  • Confirming the project builds and passes before starting work
  • Deciding how to handle a dirty working tree before syncing with main

Example prompts

  • “I just cloned the repo. Am I current, does it build, and what changed since I last worked on this?”
  • “Check my sync state against origin/main without touching my working tree.”
  • “My tree is dirty. Give me a recovery plan before we sync with main.”
  • “Build the release binary and run the verification gate, and tell me exactly what you ran.”

Requirements

  • A local checkout of the Codewhale repository
  • Rust and Cargo to build the codewhale-cli binary

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Inspect (read-only, always safe)
  2. Sync — propose, never perform
  3. Build
  4. Verification gate — the repository's exact CI command
  5. What's new — deterministic local digest
  6. Dogfood — optional, staged, confirmed

What it can do on your machine

Read from SKILL.md and the folder at commit 8d2fb45. 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:

    • git
    • cargo

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    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.

  • 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

Codewhale Contributor Onboarding loads about 1.3k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 658 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 codewhale-hq/Codewhale at commit 8d2fb45, republished under its MIT licence (© codewhale-hq). 658 words, ~1,254 tokens.

Download SKILL.mdSave it as .claude/skills/contributor-onboarding/SKILL.md (or your agent's skills folder).
name
contributor-onboarding
description
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.
invocation
explicit-only

Contributor Onboarding

A first-run path for a contributor who has cloned the repo and wants to know am I current, does it build, does it pass, and what changed while I was away — without a wall of prose and without anything touching their working tree behind their back.

Invocation

Explicit-only. Loading this skill is not authority to fetch, pull, rebase, push, or write files. Every network or mutating step below is a separate action the contributor must ask for after reading the plan.

Non-goals

  • Do not run git fetch, git pull, git rebase, or git checkout on your own initiative. Report state; propose the command; wait.
  • Do not stash, discard, reset, or commit a dirty tree. Ever.
  • Do not call a model provider. Every step here is a local command with a deterministic result. The digest is built from files and git output, not generated prose.
  • Do not claim a gate passed that you did not run, and do not summarize a build you did not observe.
  • Do not privilege any provider. Codewhale is provider-neutral; a dogfood run uses whatever route the contributor already configured, or none.

Workflow

1. Inspect (read-only, always safe)

Run these and report the results verbatim. Nothing here writes:

git rev-parse --abbrev-ref HEAD
git status --porcelain
git rev-list --left-right --count origin/main...HEAD

Report three facts plainly:

  • Branch the contributor is on.
  • Tree state: clean, or the count and paths of dirty entries.
  • Sync state: N behind, M ahead of origin/main, or unavailable when origin/main is missing or has never been fetched. Unavailable is a real answer — say it rather than guessing zero.
2. Sync — propose, never perform

If behind, print the exact commands and stop:

git fetch origin
git rebase origin/main     # or: git merge origin/main

If the tree is dirty, do not propose a sync at all. Print a recovery plan first, in this order, and let the contributor choose:

  1. git stash push -u -m "wip before sync" then sync, then git stash pop
  2. Commit the work on a branch, then sync
  3. Stay behind and continue — being behind is not an error
3. Build
cargo build --release -p codewhale-cli --bin codewhale

Report the exit status and the first error if it fails. A build failure ends the run: do not proceed to the gate and do not report gate results.

Show full SKILL.md (301 more words)Show less
4. Verification gate — the repository's exact CI command

Run what CI runs, not a paraphrase of it. Read .github/workflows/ci.yml first and run its Rust steps verbatim; the list below is a snapshot that loses to the workflow when they disagree:

cargo fmt --all -- --check
cargo clippy --workspace --all-targets --all-features --locked -- \
  -D warnings \
  -A clippy::uninlined_format_args \
  -A clippy::too_many_arguments \
  -A clippy::unnecessary_map_or
cargo test --workspace

If the workflow uses flags this snapshot lacks (or vice versa), say so and follow the workflow.

Known suite papercut: run_verifiers_background_* is flaky under full-suite parallelism and passes in isolation. Attribute it to the known flake, not to the contributor's change.

5. What's new — deterministic local digest

Built only from files already on disk. No network, no model:

git log --oneline -n 20 origin/main

plus the topmost released section of CHANGELOG.md.

Rules:

  • Cap the digest at 20 commits and 40 lines of changelog. State the cap when you hit it; do not silently truncate.
  • If origin/main is unavailable, digest HEAD instead and label it as such.
  • Quote what the files say. Do not summarize, rank, or editorialize — the point is that two contributors on the same commit get the same digest.
6. Dogfood — optional, staged, confirmed

Only after the gate has actually passed, and only if the contributor asks. Print the plan and require an explicit yes before running anything:

./target/release/codewhale exec --help

This is a provider-free smoke check: it exercises the built binary without sending a request anywhere. Anything beyond it — an actual codewhale exec turn — needs the contributor's own configured route and their explicit go-ahead. Never select a provider for them and never fall back to a default one.

Reporting

End with a compact status table: branch, tree, sync, build, gate, digest, dogfood. Use not run for anything skipped and unavailable for anything the environment could not determine. Never write passed from inference.

Credit

Requested by @JayBeest (#4227). Preserve that attribution in the changelog entry and in the commit body of any change that lands from this skill.

© 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

Files

Just SKILL.md in docs/skills/contributor-onboarding of codewhale-hq/Codewhale.

Open the folder on GitHubat commit 8d2fb45

Compare with similar skills

Codewhale Contributor Onboarding 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.

Codewhale Contributor Onboarding compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codewhale Contributor Onboarding this skillcodewhale-hq/Codewhale41k—~1.3kAutomated safety check: PassMIT
Worktrunk Release Workflowmax-sixty/worktrunk9.1k—~6.9kAutomated safety check: PassCustom licence
BrDicklesworthstone/beads_rust1.1k—~2.7kAutomated safety check: PassMIT
Guarded Git Commit and Pushjerrywu001/cc-sessions-viewer395—~603Automated safety check: NotesMIT
Stax Devcesarferreira/stax130—~987Automated safety check: PassMIT
Agentsop Aideragentsope/SkillAlchemy466—~3.5kAutomated safety check: PassMIT

Similar skills

  • Worktrunk Release Workflow

    max-sixty/worktrunk

    Walks a maintainer through cutting a Worktrunk release: sync the release branch, pass two test gates, review the changes, then publish.

    9.1k GitHub stars~6.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Br

    Dicklesworthstone/beads_rust

    Official skill for beadsrust (br), a local-first, dependency-aware issue tracker for AI agents.

    1.1k GitHub stars~2.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Guarded Git Commit and Push

    jerrywu001/cc-sessions-viewer

    Commits and pushes only on an explicit request, pulling first, running the project's CI checks locally, and stopping cold on any conflict or failure.

    395 GitHub stars~603 tokensUpdated 2 days ago
    DevelopmentAuto-check: notes
  • Stax Dev

    cesarferreira/stax

    Development harness for the stax Rust CLI project. An agent skill from cesarferreira/stax.

    130 GitHub stars~987 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Agentsop Aider

    agentsope/SkillAlchemy

    SOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format + human-in-loop REPL).

    466 GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Radicle Ecosystem

    radicle-dev/radicle-explorer

    Map of the sibling Radicle repositories that radicle-httpd depends on (heartwood, radicle-git, radicle-job, rips, radicle.dev), with the key crates and files to read in each.

    148 GitHub stars~574 tokensUpdated yesterday
    DevelopmentAuto-check passed

More from codewhale-hq/Codewhale

All 63 skills in this repo
  • Codewhale Dogfood Install

    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.

    41k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Codewhale Session Handoff

    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.

    41k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Codewhale Landing Workflow

    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.

    41k GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Sub-Agent Delegation

    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.

    41k GitHub stars~790 tokensUpdated today
    Auto-check passed
  • Codewhale Fleet Manager

    codewhale-hq/Codewhale

    Triages and manages Codewhale fleet runs and workers with typed commands, classifying failures and choosing a safe restart, resume or escalation.

    41k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • GitHub Issue Bulk Assigner

    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.

    41k GitHub stars~953 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Codewhale Contributor Onboarding

What does Codewhale Contributor Onboarding do?

Reports whether a fresh Codewhale checkout is current, builds and passes its tests, and what changed since the contributor was last here, without touching the working tree. This skill answers four questions for someone who just cloned the repository: am I current, does it build, does it pass, and what changed while I was away, without a wall of prose and without any step touching the working tree on its own initiative. Loading the skill is explicitly not authority to fetch, pull, rebase, push or write files; every network or mutating step is a separate action the contributor must ask for after reading the plan, and a dirty tree is never stashed, discarded, reset or committed.

When should I use Codewhale Contributor Onboarding?

Codewhale Contributor Onboarding fits situations like: getting oriented right after cloning the Codewhale repository; checking whether a checkout is behind main and what changed since it was last synced; confirming the project builds and passes before starting work; deciding how to handle a dirty working tree before syncing with main.

How do I install Codewhale Contributor Onboarding in Claude Code?

Run `npx skills add codewhale-hq/Codewhale --skill contributor-onboarding -a claude-code`. Or copy the skill folder (docs/skills/contributor-onboarding in codewhale-hq/Codewhale) into .claude/skills/contributor-onboarding in your project. Claude Code loads it when a task matches its description.

How do I install Codewhale Contributor Onboarding in Codex?

Run `npx skills add codewhale-hq/Codewhale --skill contributor-onboarding -a codex`. Or copy the skill folder (docs/skills/contributor-onboarding in codewhale-hq/Codewhale) into .agents/skills/contributor-onboarding in your project. Codex loads it when a task matches its description.

Can I use Codewhale Contributor Onboarding 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 codewhale-hq/Codewhale --skill contributor-onboarding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/contributor-onboarding, .gemini/skills/contributor-onboarding, .github/skills/contributor-onboarding and .opencode/skills/contributor-onboarding in your project.

What does Codewhale Contributor Onboarding need to run?

Going by SKILL.md and its folder, Codewhale Contributor Onboarding needs the command-line tools its instructions call (git and cargo). Our summary lists: A local checkout of the Codewhale repository; Rust and Cargo to build the codewhale-cli binary.

Does Codewhale Contributor Onboarding access the network?

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.

Is Codewhale Contributor Onboarding 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 Codewhale Contributor Onboarding use?

Codewhale Contributor Onboarding 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 Codewhale Contributor Onboarding use?

About 1.3k tokens (SKILL.md is roughly 5k 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 Codewhale Contributor Onboarding?

Skills that share tags, products or a category with Codewhale Contributor Onboarding: Worktrunk Release Workflow (max-sixty/worktrunk, 9.1k stars), Br (Dicklesworthstone/beads_rust, 1.1k stars), Guarded Git Commit and Push (jerrywu001/cc-sessions-viewer, 395 stars) and Stax Dev (cesarferreira/stax, 130 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codewhale Contributor Onboarding?

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.