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.
git clone --depth 1 https://github.com/catlog22/Claude-Code-WorkflowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/catlog22/claude-code-workflow/integration-test-cycle)<a href="https://agentmods.dev/commands/catlog22/claude-code-workflow/integration-test-cycle"><img src="https://agentmods.dev/badge/commands/catlog22/claude-code-workflow/integration-test-cycle/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/catlog22/claude-code-workflow/integration-test-cycle"><img src="https://agentmods.dev/badge/commands/catlog22/claude-code-workflow/integration-test-cycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00030 | $0.09043 |
| Opus 5.5 | $0.00012 | $0.03617 |
| Sonnet 5.5 | $0.00006 | $0.01809 |
| Haiku 4.5 | $0.00003 | $0.00904 |
Grade A, and why
integration-test-cycle 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 1mo 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 — 1,077 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Mode
When --yes or -y: Auto-confirm exploration decisions, use recommended test strategies, skip interactive checkpoints.
Workflow Integration-Test-Cycle Command
Quick Start
# Basic - explore and test a module
/workflow:integration-test-cycle "用户认证模块的集成测试"
# Auto mode - fully autonomous
/workflow:integration-test-cycle -y "支付流程端到端集成测试"
# Continue interrupted session
/workflow:integration-test-cycle --continue "认证模块"
# Custom iteration limit
/workflow:integration-test-cycle --max-iterations=15 "API网关集成测试"
Context Source: cli-explore-agent + Gemini/Claude analysis
Output Directory: .workflow/.integration-test/{session-id}/
Core Innovation: Reflection-driven self-iterating test cycle with documented learning evolution
What & Why
Core Concept
Unified integration test workflow: Explore → Design → Develop → Test → Reflect → Adjust → Re-test — a closed-loop that autonomously improves test quality through text-based reflection.
vs Existing Commands:
- test-fix-gen: Only generates test tasks, requires manual
workflow-test-fixskill - test-cycle-execute: Only executes pre-existing tasks, no exploration or test design
- This command: Full lifecycle — from zero knowledge to passing integration tests, with self-reflection
Value Proposition
- Zero-to-Tests: No prior session needed — starts from exploration
- Self-Improving: Reflection log drives strategy adjustment between iterations
- Integration Focus: Specifically targets cross-module boundaries and API contracts
- Documented Learning: Every decision, failure, and adjustment recorded in reflection-log.md
Output Artifacts
2 核心文件 + 1 追踪目录，全流程产物最小化：
| Artifact | Type | Description |
|---|---|---|
reflection-log.md |
人类可读 | ⭐ 唯一文本文档：探索发现、设计决策、迭代反思、累积认知、最终结论 |
state.json |
机器可读 | 唯一状态文件：探索上下文、测试设计、测试清单、迭代状态、测试结果、修复历史、最终摘要 |
.trace/ |
原始日志 | CLI 输出和测试日志，仅调试用：cli-{N}.txt、test-output.log |
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.
- 1mo ago First seen · 1,077 lines · 30 tokens per session scan A 59abd6defa9b
integration-test-cycle is a command published in the GitHub repository catlog22/Claude-Code-Workflow (2,124 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 9,043 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
prp-implement
Execute an implementation plan with rigorous validation loops.
9_gofer_tests
Generate comprehensive test suites from four testing perspectives for a target component.
test
Write tests before implementation using Red-Green-Refactor.
red-team
description: "Red team AI system for vulnerabilities".
evaluate
Evaluate a skill across model tiers using blind testing.
svelte:test-coverage
Analyze test coverage, identify testing gaps, and provide recommendations for improving test coverage in Svelte/SvelteKit projects.