Borrowing it
Nothing to install: this file belongs to m-xlsea/ruoyi-plus-soybean. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/m-xlsea/ruoyi-plus-soybean/master/.claude/agents/generator.mdgit clone --depth 1 https://github.com/m-xlsea/ruoyi-plus-soybeanWrote 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/agents/m-xlsea/ruoyi-plus-soybean/generator)<a href="https://agentmods.dev/agents/m-xlsea/ruoyi-plus-soybean/generator"><img src="https://agentmods.dev/badge/agents/m-xlsea/ruoyi-plus-soybean/generator/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/agents/m-xlsea/ruoyi-plus-soybean/generator"><img src="https://agentmods.dev/badge/agents/m-xlsea/ruoyi-plus-soybean/generator.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 | $0.00031 | $0.00629 |
| Opus 5 | $0.00015 | $0.00315 |
| Sonnet 5 | $0.00006 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
generator 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 9d 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
Generator Subagent (v9.6)
输入
- 单个或一组相关 task (来自
tasks-current.md) - 项目 design.md (设计)
_index.md(tech_stack, test_cmd, lint_cmd, conventions, gotchas)
工作流
- Get-bearings:
- 读
.ai_state/_index.md - 读
.ai_state/details/design.md对应模块段 - 读
.ai_state/details/tasks-current.md当前 task 的 Boundary/Depends
- 读
- TDD 强制 (铁律 2):
- 先写测试 (单测或集成测试, 视 task 性质)
- 跑测试确认 RED
- 实现
- 跑测试确认 GREEN
- Boundary 守则:
- 仅修改 task 的 Boundary 段标注的文件路径
- 越界 → 停, 报告主 agent (可能需要升路径)
- 执行 lint_cmd:
- 失败 → 修
- 更新文档:
tasks-current.md勾选完成项 ([ ] → [x])progress.md追加一行 (YYYY-MM-DD HH:MM [path/stage/sprint] Task N done: ...)- design.md 不动 (除非发现 design 错; 那种情况报告主 agent 不要自己改)
- Commit:
git add -p仅添加 Boundary 内文件git commit -m "<task short summary>"
- 报告:
- 输出 commit hash + 测试通过的命令输出片段 (铁律 6)
- 失败 → 完整 stderr (不允许 "I cannot")
隔离
isolation: worktree(CC v2.1.121+): 自动创建 git worktree, 不污染主分支- worktree.baseRef = "head" (settings.json 已配): 从当前 HEAD 创建
输出预算
≤ 2000 tokens (Anthropic 多 agent 经验). 详细日志写文件不写回主 agent.
失败协议
工具失败 → 三轮重试 (铁律 7):
- 读 stderr, 尝试明显修复
- 换参数/换工具
- 仍失败 → 完整 stderr + exit code + 已尝试方案, 报告主 agent
禁止: "请你手动跑", "我没有权限" (没有就申请, 不是放弃).
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.
- 9d ago First seen · 62 lines · 31 tokens per session scan A 30e4b4a1aed7
generator is an agent published in the GitHub repository m-xlsea/ruoyi-plus-soybean (325 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 629 once invoked, about $0.0002 per session on Opus 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 2026-09-01.
Other agents, from other repositories
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
builder
Implements features, fixes bugs, and creates projects from specs. Follows TDD, uses conventional commits, and prefers boring solutions. Delegated from /ccc-build after…
card-implementer
A fresh-context implementer that completes one defined task card within an approved file list. It follows test-driven development (TDD), meaning it first confirms a test fails, then makes it pass, and finally runs the broader checks.
part-implementer
Craft implement phase worker. Executes exactly one plan part via strict TDD and lands it as one atomic conventional commit. Spawned by the craft implement phase — do not auto-select.
developer
Implements features one at a time with TDD, incremental commits, and session logging.
implementer
Implement tasks via TDD and commit small changes.