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/phased-plangit 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 | $0.00928 |
| Opus 5 | $0.00000 | $0.00464 |
| Sonnet 5 | $0.00000 | $0.00186 |
| Haiku 4.5 | $0.00000 | $0.00093 |
Grade A, and why
phased-plan 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/phased-plan — Generate 7-Phase Implementation Plan
Arguments
$ARGUMENTS— Story ID to plan (e.g., "US-001")
Instructions
You are generating a 7-phase implementation plan that maps a user story to the structured development workflow.
Story input: $ARGUMENTS
Step 1: Read the Story
Find and read the user story at docs/stories/{story-ID}.md. If it doesn't exist, tell the user to run /story first. Also read the referenced PRD for full context.
Step 2: Map to 7 Phases
Generate a plan at docs/plans/PLAN-{story-ID}.md that maps the story's BDD scenarios to concrete deliverables across all 7 phases:
# Implementation Plan: {Story ID} — {Story Title}
## Source Story
- Story: docs/stories/{story-ID}.md
- PRD: {PRD path}
## Phase 1: Presentational UI
**Agent:** frontend-phase-1
**Goal:** Build pure UI components with no business logic
### Deliverables
- [ ] `apps/web/src/components/{ComponentName}.tsx` — {description}
- [ ] `apps/web/src/components/__tests__/{ComponentName}.test.tsx`
### BDD Mapping
- Scenario "{name}" → renders {component} with {props}
---
## Phase 2: API Client & Mocks
**Agent:** frontend-phase-2
**Goal:** Create API hooks and MSW mock handlers
### Deliverables
- [ ] `apps/web/src/lib/api/{resource}.ts` — TanStack Query hooks
- [ ] `apps/web/src/mocks/handlers/{resource}.ts` — MSW handlers
- [ ] `libs/shared/src/types/{resource}.ts` — Shared response types
### API Contract
| Method | Endpoint | Request | Response |
|--------|----------|---------|----------|
| GET | /api/... | — | {...} |
---
## Phase 3: Smart Components & State
**Agent:** frontend-phase-3
**Goal:** Wire UI to state and API hooks
### Deliverables
- [ ] `apps/web/src/stores/{store}.ts` — Zustand store
- [ ] `apps/web/src/app/{route}/page.tsx` — Page component
- [ ] Integration tests for user flows
---
## Phase 4: Repository Layer (TDD)
**Agent:** backend-phase-4
**Goal:** Build data access with tests first
### Deliverables
- [ ] `apps/api/src/modules/{module}/domain/{entity}.ts`
- [ ] `apps/api/src/modules/{module}/{module}.repository.ts`
- [ ] `apps/api/src/modules/{module}/{module}.repository.spec.ts`
### Database Schema
Tables and columns needed for this feature.
---
## Phase 5: Service Layer (TDD)
**Agent:** backend-phase-5
**Goal:** Implement business logic with mocked repos
### Deliverables
- [ ] `apps/api/src/modules/{module}/{module}.service.ts`
- [ ] `apps/api/src/modules/{module}/{module}.service.spec.ts`
### Business Rules
Logic and validation rules derived from BDD scenarios.
---
## Phase 6: Controller Layer (TDD)
**Agent:** backend-phase-6
**Goal:** Thin controllers with E2E tests
### Deliverables
- [ ] `apps/api/src/modules/{module}/{module}.controller.ts`
- [ ] `apps/api/src/modules/{module}/{module}.module.ts`
- [ ] `apps/api/src/modules/{module}/{module}.e2e.spec.ts`
---
## Phase 7: Integration
**Agent:** integration-phase-7
**Goal:** Connect frontend to real backend, verify E2E
### Deliverables
- [ ] Remove/disable MSW mocks for this feature
- [ ] Configure real API endpoint
- [ ] E2E smoke test passing
### Verification
- [ ] All BDD scenarios pass as integration tests
- [ ] No MSW handlers active for production paths
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 · 125 lines · 0 tokens per session scan A dfad9e90521a
phased-plan 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 928 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.