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
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Hmbown/CodeWhale --skill helpgit clone --depth 1 https://github.com/Hmbown/CodeWhaleWrote 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/help)<a href="https://agentmods.dev/skills/hmbown/codewhale/help"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/help/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hmbown/codewhale/help"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.00595 |
| Opus 5.5 | $0.00014 | $0.00238 |
| Sonnet 5.5 | $0.00007 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
help 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 23d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help
Invocation
Explicit-only. This skill is a router, not a manual. It is deliberately kept out of the ambient model catalogue so it never spends prompt budget, and it never restates documentation that the running build already exposes.
When to use
Load it only when the user explicitly asks how to use Codewhale itself — a command, a setting, a keybinding, or where a feature lives.
Non-goals
- Do not paste a manual, a command list, or a settings table into context.
- Do not answer from memory of another harness; Codewhale's surfaces differ.
- Do not guess at flags, config keys, or paths. Read them, or say you did not.
Routing table
Answer from the surface that owns the fact, in this order:
- Slash commands —
/helplists the commands this build registers;/help <command>prints that command's usage line. This is the only authoritative command list, because it is generated from the registry. - Skills —
/skillsopens the manager,/skills inspectprints the discovery mode, searched directories, and source paths./skill <name>activates one. Seedocs/SKILLS.mdin a Codewhale checkout. - Configuration —
/configis the live settings surface. Config file keys are documented indocs/CONFIGURATION.md; provider/model routing indocs/PROVIDERS.md. - Keybindings —
docs/KEYBINDINGS.mdin a checkout. There is no keybinding slash command; do not invent one. - Environment problems —
codewhale-tui doctorreports the resolved config path, provider credential presence (never values), and workspace state. Prefer its output over inference.
Working in a Codewhale checkout
When the workspace is a Codewhale checkout, docs/ is present on disk and
the read tool (path: "docs/...") is the right tool. Read the single most relevant file and quote
the specific lines. Outside a checkout, docs/ is usually absent — in that
case rely on /help, /config, and doctor, and say plainly that the
reference docs are not installed locally.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 23d ago Changed ca06a265af80
- 1mo ago First seen · 52 lines · 36 tokens per session scan A 3e03eda8e958
help is a skill published in the GitHub repository Hmbown/CodeWhale (41,081 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 595 once invoked, about $0.0001 per session on Opus 5.5. 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-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.
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-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-handoff
Use when writing a Codewhale takeover prompt, continuation note, or end-of-session summary for another agent or a later session: a paste-ready handoff grounded in live state, with done/suspected/blocked kept separate.
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.