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/touheedcode/claude-dev-workflow/commitgit clone --depth 1 https://github.com/TouheedCode/claude-dev-workflowWhat 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 | $0.00000 | $0.00524 |
| Opus 5 | $0.00000 | $0.00262 |
| Sonnet 5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
commit 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.
What it actually says
/commit — Phase-Scoped Conventional Commit
Arguments
$ARGUMENTS— Optional: phase number or custom scope (e.g., "Phase 3", "docs")
Instructions
You are creating a conventional commit scoped to the current phase of work.
Input: $ARGUMENTS
Step 1: Determine Scope
Check .phase-context.json for the current story and phase context. Determine:
- Story ID (e.g.,
US-001) - Phase number (from arguments or the latest completed phase in context)
- Phase name (e.g., "presentational-ui", "api-client", "repository-layer")
Phase scope mappings:
| Phase | Scope |
|---|---|
| 1 | ui |
| 2 | api-client |
| 3 | smart-components |
| 4 | repository |
| 5 | service |
| 6 | controller |
| 7 | integration |
Step 2: Analyze Changes
Run git diff --staged and git diff to understand what changed. Categorize:
- New files — these are
feattype - Modified files — could be
feat,fix,refactor - Test files — these support the main type
- Config changes — these are
chore
Step 3: Generate Commit Message
Follow conventional commits format:
{type}({scope}): {short description}
{body — what was built and why}
Story: {story-ID}
Phase: {N}/7 — {phase title}
Examples:
feat(ui): add TaskCard and TaskList components
Build presentational components for task display with TypeScript
props, Tailwind styling, and unit tests.
Story: US-001
Phase: 1/7 — Presentational UI
feat(repository): add task repository with Testcontainers tests
Implement Drizzle-based TaskRepository with full CRUD operations.
Tests use Testcontainers with real PostgreSQL.
Story: US-001
Phase: 4/7 — Repository Layer
Step 4: Execute
- Stage all relevant files:
git add {files} - Create the commit with the generated message
- Print the commit hash and summary
- If this is Phase 7, remind the user to run
/prto create the pull request
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 · 79 lines · 0 tokens per session scan A 3353da207010
commit is a command published in the GitHub repository TouheedCode/claude-dev-workflow (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 524 tokens. 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 2026-08-31.
Other commands, from other repositories
auto-work
给一个需求,AI自动完成调研→方案→方案Review→开发→开发Review全流程.
develop-review
Review feature-developing 生成的代码,检查遗漏和宪法违规.
developing
Command "developing" from chaohong-ai/ai-auto-work, covering 参数解析, 你的角色, 工作流程, 第一步:建立完整上下文 and 第二步:确认实现范围.
manual-work
带人工检查点的开发流程:前期需求/方案重点把关,后期自主执行.
plan-review
Review生成的plan,检查边界情况、场景覆盖、架构合理性.
analyze
分析 auto-work 产出中遗漏/缺陷的根因,定位流程断点并输出修复方案+工作流优化建议.