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 commands/codelably/harmony-claude-code/skill-creategit clone --depth 1 https://github.com/codelably/harmony-claude-codeWhat 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 | $0.00032 | $0.01372 |
| Opus 5 | $0.00016 | $0.00686 |
| Sonnet 5 | $0.00006 | $0.00274 |
| Haiku 4.5 | $0.00003 | $0.00137 |
Grade A, and why
skill-create 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.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/skill-create - 本地技能生成(Local Skill Generation)
分析你仓库的 Git 历史记录以提取编码模式,并生成 SKILL.md 文件,以便让 Claude 学习你团队的工程实践。
用法(Usage)
/skill-create # 分析当前仓库
/skill-create --commits 100 # 分析最近 100 条提交
/skill-create --output ./skills # 指定自定义输出目录
/skill-create --instincts # 同时为 continuous-learning-v2 生成直觉(instincts)
功能说明(What It Does)
- 解析 Git 历史 - 分析提交(commits)、文件变更和模式。
- 检测模式 - 识别循环出现的工作流(Workflow)和约定。
- 生成 SKILL.md - 创建有效的 Claude Code 技能(Skill)文件。
- 可选生成直觉(Instincts) - 用于 continuous-learning-v2 系统。
分析步骤(Analysis Steps)
第 1 步:收集 Git 数据
# 获取带有文件变更的近期提交
git log --oneline -n ${COMMITS:-200} --name-only --pretty=format:"%H|%s|%ad" --date=short
# 获取按文件统计的提交频率
git log --oneline -n 200 --name-only | grep -v "^$" | grep -v "^[a-f0-9]" | sort | uniq -c | sort -rn | head -20
# 获取提交信息模式
git log --oneline -n 200 | cut -d' ' -f2- | head -50
第 2 步:检测模式
寻找以下模式类型:
| 模式 (Pattern) | 检测方法 (Detection Method) |
|---|---|
| 提交规范 (Commit conventions) | 对提交信息使用正则匹配 (feat:, fix:, chore:) |
| 文件关联变更 (File co-changes) | 总是同时发生变化的文件 |
| 工作流序列 (Workflow sequences) | 重复出现的文件变更模式 |
| 架构 (Architecture) | 文件夹结构和命名规范 |
| 测试模式 (Testing patterns) | 测试文件位置、命名、覆盖率 |
第 3 步:生成 SKILL.md
输出格式:
---
name: {repo-name}-patterns
description: Coding patterns extracted from {repo-name}
version: 1.0.0
source: local-git-analysis
analyzed_commits: {count}
---
# {Repo Name} 模式
## 提交规范
{检测到的提交信息模式}
## 代码架构
{检测到的文件夹结构和组织方式}
## 工作流
{检测到的重复文件变更模式}
## 测试模式
{检测到的测试约定}
第 4 步:生成直觉 (如果使用了 --instincts)
用于 continuous-learning-v2 集成:
---
id: {repo}-commit-convention
trigger: "when writing a commit message"
confidence: 0.8
domain: git
source: local-repo-analysis
---
# 使用约定式提交 (Conventional Commits)
## 操作 (Action)
在提交信息前添加前缀:feat:, fix:, chore:, docs:, test:, refactor:
## 证据 (Evidence)
- 已分析 {n} 条提交
- {percentage}% 遵循约定式提交格式
输出示例
在 TypeScript 项目上运行 /skill-create 可能会产生:
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 · 175 lines · 32 tokens per session scan A 80447d475970
skill-create is a command published in the GitHub repository codelably/harmony-claude-code (42 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 1,372 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 commands, from other repositories
verify
Adversarial spec-vs-implementation verification for a completed task. Dispatches the spec-mentor subagent with fresh context (no anchoring bias), parses its verdict (PASS / DRIFT / NEEDS-MARTY), and updates the verification queue. The v7.4.0 architectural replacement for a dedicated "mentor session.".
research
Enter RESEARCH mode for information gathering.
criar-skill
Use when creating new skills, automations, or specialized knowledge packages. Keywords: criar skill, nova skill, automatizar, conhecimento, TDD skill.
research
Delegate a thorough research investigation to the agy:runner subagent.
station
You are helping the user work with Station - the self-hosted AI agent orchestration platform.
delegate
Delegate investigation, an explicit fix request, or follow-up work to the Grok delegate subagent.