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/softaworks/agent-toolkit/command-creatornpx skills add softaworks/agent-toolkit --skill command-creatorgit clone --depth 1 https://github.com/softaworks/agent-toolkitWhat 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 | $0.00066 | $0.01564 |
| Opus 5 | $0.00033 | $0.00782 |
| Sonnet 5 | $0.00013 | $0.00313 |
| Haiku 4.5 | $0.00007 | $0.00156 |
Grade A, and why
command-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 yesterday.
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.
This is a copy
100% identical to command-creator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command Creator
This skill guides the creation of Claude Code slash commands - reusable workflows that can be invoked with /command-name in Claude Code conversations.
About Slash Commands
Slash commands are markdown files stored in .claude/commands/ (project-level) or ~/.claude/commands/ (global/user-level) that get expanded into prompts when invoked. They're ideal for:
- Repetitive workflows (code review, PR submission, CI fixing)
- Multi-step processes that need consistency
- Agent delegation patterns
- Project-specific automation
When to Use This Skill
Invoke this skill when users:
- Ask to "create a command" or "make a slash command"
- Want to automate a repetitive workflow
- Need to document a consistent process for reuse
- Say "I keep doing X, can we make a command for it?"
- Want to create project-specific or global commands
Bundled Resources
This skill includes reference documentation for detailed guidance:
- references/patterns.md - Command patterns (workflow automation, iterative fixing, agent delegation, simple execution)
- references/examples.md - Real command examples with full source (submit-stack, ensure-ci, create-implementation-plan)
- references/best-practices.md - Quality checklist, common pitfalls, writing guidelines, template structure
Load these references as needed when creating commands to understand patterns, see examples, or ensure quality.
Command Structure Overview
Every slash command is a markdown file with:
---
description: Brief description shown in /help (required)
argument-hint: <placeholder> (optional, if command takes arguments)
---
# Command Title
[Detailed instructions for the agent to execute autonomously]
Command Creation Workflow
Step 1: Determine Location
Auto-detect the appropriate location:
- Check git repository status:
git rev-parse --is-inside-work-tree 2>/dev/null - Default location:
- If in git repo → Project-level:
.claude/commands/ - If not in git repo → Global:
~/.claude/commands/
- If in git repo → Project-level:
- Allow user override:
- If user explicitly mentions "global" or "user-level" → Use
~/.claude/commands/ - If user explicitly mentions "project" or "project-level" → Use
.claude/commands/
- If user explicitly mentions "global" or "user-level" → Use
What ships with it
4 files 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.
- yesterday First seen · 211 lines · 66 tokens per session scan A 250a46ebe34c
command-creator is a skill published in the GitHub repository softaworks/agent-toolkit (2,401 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 1,564 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to command-creator, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…