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/skill-creatornpx skills add Hmbown/CodeWhale --skill skill-creatorgit 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/skill-creator)<a href="https://agentmods.dev/skills/hmbown/codewhale/skill-creator"><img src="https://agentmods.dev/badge/skills/hmbown/codewhale/skill-creator.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 | $0.00051 | $0.00876 |
| Opus 5 | $0.00026 | $0.00438 |
| Sonnet 5 | $0.00010 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
skill-creator 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 4d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
Use this skill to create small, useful codewhale skills that match the runtime this repository actually ships.
What A Skill Is
A skill is a local folder with a SKILL.md file. DeepSeek reads the skill name
and description during discovery, then loads the body only when the user or task
matches the skill.
Discovery paths, in precedence order:
<workspace>/.agents/skills<workspace>/skills<workspace>/.opencode/skills<workspace>/.claude/skills<workspace>/.cursor/skills<workspace>/.codewhale/skills~/.agents/skills~/.claude/skills~/.codewhale/skills~/.deepseek/skills(legacy fallback)
Use skills for model instructions, workflows, and lightweight conventions. Use MCP for live external APIs or durable tools. Use hooks for automatic local events. Use plugin folders only as packaging/scaffolding until a real plugin loader exists.
Minimum Shape
my-skill/
`-- SKILL.md
---
name: my-skill
description: Use when Codewhale should follow this specific workflow.
---
# My Skill
Instructions for the agent.
Frontmatter parsing is intentionally simple. Keep name and description as
plain single-line values. Use lower-case hyphen-case names.
Writing Rules
- Make the
descriptionaction-oriented and trigger-specific. It is the main signal DeepSeek sees before loading the body. - Keep the body operational. Include what to do, what to avoid, and how to verify the result.
- Do not include general programming advice, marketing copy, or long background material.
- Move bulky details to
references/and mention exactly when to open them. - Add
scripts/only for deterministic helpers that are worth maintaining. - Add
assets/only for templates, fixtures, examples, or files reused by the workflow. - Do not assume scripts are safe to run. Community skill scripts require user intent and trust review.
Creation Workflow
- Define the skill boundary in one sentence.
- Decide whether a skill is the right surface:
- Instructional workflow: skill
- External service/API: MCP server plus an optional skill
- Repeated shell helper: local tool or script plus an optional skill
- Packaging multiple pieces: plugin scaffold plus skill/MCP activation notes
- Create
<skill-name>/SKILL.md. - Write frontmatter with
nameanddescription. - Write a concise body with:
- trigger and scope
- required inputs or assumptions
- step-by-step workflow
- validation checks
- safety notes
- Add companion files only when they reduce real complexity.
- Validate by loading the skill through
/skillsor by running the relevant skill discovery tests if editing this repository.
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.
- 4d ago First seen · 111 lines · 51 tokens per session scan A 6bc62cc2c0c6
skill-creator is a skill published in the GitHub repository Hmbown/CodeWhale (40,889 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 876 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
claw-orchestrator
Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Grok Build, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel…
ultraapp-interview
Use when the user opens a Forge tab in the claw-orchestrator dashboard to start building a new ultraapp. Drives a structured Q&A interview that produces a complete AppSpec, then signals readiness to build.
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.