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/validategit 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 | $0.01348 |
| Opus 5 | $0.00000 | $0.00674 |
| Sonnet 5 | $0.00000 | $0.00270 |
| Haiku 4.5 | $0.00000 | $0.00135 |
Grade A, and why
validate 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/validate — Quality Gate
Arguments
$ARGUMENTS— Phase identifier (e.g., "Phase 1", "Phase 3") and optionally the story ID
Instructions
You are the quality gate. Your job is to verify that a phase's implementation meets quality standards before the team moves to the next phase. No phase should advance until validation passes.
Input: $ARGUMENTS
Step 1: Parse Arguments
Extract:
- Phase number (1–7)
- Story ID — if not provided, read from
.phase-context.json
Step 2: Load Expected Deliverables
Read the plan at docs/plans/PLAN-{story-ID}.md and extract the deliverable checklist for the target phase. Each deliverable should have an exact file path.
Step 3: Run Validation Checks
Execute these checks in order. Record pass/fail for each.
Check 1: File Existence
For each deliverable file path in the plan:
- Verify the file exists at the specified path
- Verify the file is non-empty (> 0 bytes)
- Record:
{passed}/{total} files
Check 2: Build
Run the build to catch compilation and type errors early:
# Frontend phases (1-3)
cd apps/web && npx tsc --noEmit
# Backend phases (4-6)
cd apps/api && npx tsc --noEmit
# Phase 7: Both
npm run typecheck
- Record: clean or error count
Check 3: Tests Pass
Run tests scoped to this phase's files:
| Phase | Command |
|---|---|
| 1 | npx vitest run apps/web/src/components/__tests__/ |
| 2 | (no tests — types and hooks only; verify types compile in Check 2) |
| 3 | npx vitest run apps/web/src/app/ |
| 4 | npx vitest run apps/api/src/modules/{module}/__tests__/{module}.repository.integration.spec.ts |
| 5 | npx vitest run apps/api/src/modules/{module}/__tests__/{module}.service.spec.ts |
| 6 | npx vitest run apps/api/src/modules/{module}/__tests__/{module}.e2e.spec.ts |
| 7 | npm run test (full suite) |
- Record:
{passed}/{total} tests - Note: Phase 4 requires Docker running for Testcontainers. If Docker is unavailable, report as
SKIP(not fail).
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 · 164 lines · 0 tokens per session scan A 9469cd096d81
validate 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 1,348 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.