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/implementgit 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 | $0.00959 |
| Opus 5 | $0.00000 | $0.00479 |
| Sonnet 5 | $0.00000 | $0.00192 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
implement 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/implement — Phase Dispatcher
Arguments
$ARGUMENTS— Phase identifier (e.g., "Phase 1", "Phase 3", "Phase 7") and optionally the story ID
Instructions
You are the phase dispatcher. Your job is to route implementation work to the correct phase agent with the right context.
Input: $ARGUMENTS
Step 1: Parse Arguments
Extract:
- Phase number (1–7) from the arguments
- Story ID (optional) — if not provided, look for the most recent plan in
docs/plans/PLAN-*.md
Step 2: Load the Plan
Read the plan file at docs/plans/PLAN-{story-ID}.md. If it doesn't exist, tell the user to run /phased-plan first.
Extract the section for the target phase, including:
- Deliverables (file paths)
- BDD mapping or business rules
- Any phase-specific context (API contract, database schema, etc.)
Step 3: Load Phase Context Chain
Read .phase-context.json from the project root. This file tracks outputs from completed phases.
See docs/phase-context-chaining.md for the full format specification.
If the file exists:
- Verify the
storyIdmatches - Check that prerequisite phases are in
completedPhases:- Phase 1: no prerequisites
- Phase 2: Phase 1 complete
- Phase 3: Phases 1 and 2 complete
- Phase 4: Phase 2 complete (shared types needed)
- Phase 5: Phase 4 complete
- Phase 6: Phase 5 complete
- Phase 7: Phases 1–6 complete
- Extract relevant
phaseOutputsfor the target phase
If the file doesn't exist:
- Phase 1: Create it with story metadata
- Phase 2+: Warn the user. Offer to scan existing files and reconstruct context, or ask them to re-run earlier phases.
Step 4: Dispatch to Agent
Load the correct agent file based on phase number:
| Phase | Agent File |
|---|---|
| 1 | .claude/agents/frontend-phase-1.md |
| 2 | .claude/agents/frontend-phase-2.md |
| 3 | .claude/agents/frontend-phase-3.md |
| 4 | .claude/agents/backend-phase-4.md |
| 5 | .claude/agents/backend-phase-5.md |
| 6 | .claude/agents/backend-phase-6.md |
| 7 | .claude/agents/integration-phase-7.md |
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 · 114 lines · 0 tokens per session scan A 188d8cf448da
implement 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 959 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.