Hmbown/CodeWhale is an open-source coding agent that runs in the terminal and is written in Rust. Developers use it to inspect repositories, edit files, run commands, and coordinate work with configurable model providers, skills, MCP servers, and approval controls; the catalogue entries extend its available workflows.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Hmbown/CodeWhalenpx agentmods add skills/hmbown/codewhale/contributor-onboardingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hmbown/codewhale/contributor-onboarding)<a href="https://agentmods.dev/skills/hmbown/codewhale/contributor-onboarding"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/contributor-onboarding.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01229 |
| Opus 5 | $0.00028 | $0.00615 |
| Sonnet 5 | $0.00011 | $0.00246 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
contributor-onboarding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributor Onboarding
Requested by @JayBeest in issue #4227: 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, orgit checkouton 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 aheadoforigin/main, or unavailable whenorigin/mainis 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:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 145 lines · 57 tokens per session scan A 0f5dfb27e4de
contributor-onboarding is a skill published in the GitHub repository Hmbown/CodeWhale (40,914 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,229 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cw-dogfood
Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
cw-orient
Use at the start of any Codewhale work session, or when unsure which checkout, branch, or worktree is authoritative: establish live repo truth before reading a plan or editing a file.
computer-use
Full desktop control on macOS, Windows, Linux, and HarmonyOS — accessibility-first observation and actions with pixel fallback, screenshots, zoom, screen recording, and switching between registered computers as a default.
cw-slice
Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.