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 agentmods add skills/hmbown/codewhale/helpnpx skills add Hmbown/CodeWhale --skill helpgit clone --depth 1 https://github.com/Hmbown/CodeWhaleWhat 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 | $0.00036 | $0.00592 |
| Opus 5 | $0.00018 | $0.00296 |
| Sonnet 5 | $0.00007 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
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 2d 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
File with action: "read" 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 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.
- 2d ago First seen · 52 lines · 36 tokens per session scan A 3e03eda8e958
help is a skill published in the GitHub repository Hmbown/CodeWhale (40,889 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 592 once invoked, about $0.0002 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
write-zot-themes
Help the user create, install, or package zot themes, including theme-only extensions.
visual-acceptance
UI/视觉改动交付前的终验方法论——多主题截图矩阵复现、像素真值判据链、CSS 层叠陷阱、布局漂移审查、before/after 存证。当视觉改动需要验收(而非实现)时使用:交付前最后一环,回答「看得见的部分真的对吗」。.
code-review
Run a thorough self-review pass on the most recent change.
design-prototype
Frontend UI prototype workflow — clarify intent, explore directions, preview across viewports, diff against references, deliver with screenshot evidence.
test-fix
Diagnose and minimally fix a failing test, then re-run.
office-docx
生成与读取 Word 文档(.docx)——报告、合同、交付文档、投标书;原生 docx 渲染,支持 heading/paragraph/table/code/list 内容块与居中标题.