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/storygit 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 | $0.00500 |
| Opus 5 | $0.00000 | $0.00250 |
| Sonnet 5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
story 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.
What it actually says
/story — Generate User Story with BDD Scenarios
Arguments
$ARGUMENTS— Story ID and title (e.g., "US-001 User can create a new task")
Instructions
You are generating a User Story with BDD (Behavior-Driven Development) scenarios.
Story input: $ARGUMENTS
Step 1: Parse Input
Extract the story ID (e.g., US-001) and the story title from the arguments. If no ID is provided, ask the user for one.
Step 2: Find the PRD
Look for PRD files in docs/PRD-*.md. If multiple exist, ask the user which PRD this story belongs to. Read the PRD to understand the project context, features, and constraints.
Step 3: Generate the User Story
Create the story file at docs/stories/{story-ID}.md with this structure:
# {Story ID}: {Story Title}
## User Story
As a [type of user],
I want [action/goal],
So that [benefit/value].
## BDD Scenarios
### Scenario 1: {Happy path name}
**Given** [precondition]
**When** [action taken]
**Then** [expected outcome]
**And** [additional outcome if needed]
### Scenario 2: {Alternative path name}
**Given** [precondition]
**When** [action taken]
**Then** [expected outcome]
### Scenario 3: {Error/edge case name}
**Given** [precondition]
**When** [action taken]
**Then** [expected error handling]
## Acceptance Criteria
- [ ] {Criterion 1 — derived from scenarios}
- [ ] {Criterion 2}
- [ ] {Criterion 3}
## Technical Notes
Any implementation hints, API endpoints needed, data models involved, or dependencies on other stories.
## Dependencies
- PRD: {link to PRD file}
- Blocked by: {other story IDs, if any}
Step 4: Output
- Write the story to
docs/stories/{story-ID}.md - Print a summary: story ID, title, number of BDD scenarios, and file path
- Remind the user to run
/phased-plannext to create an implementation plan for this story
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 · 69 lines · 0 tokens per session scan A 3880390c5b78
story is a command published in the GitHub repository TouheedCode/claude-dev-workflow (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 500 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.
fast-auto-work
面向小改动的快速开发流程，跳过调研/方案/验收文档，只做实现+编译+相关测试.
plan-review
Review生成的plan，检查边界情况、场景覆盖、架构合理性.