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 skills add PANYUXIN6/pyx-skills --skill simplify-codebasegit clone --depth 1 https://github.com/PANYUXIN6/pyx-skillsWrote 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/skills/panyuxin6/pyx-skills/simplify-codebase)<a href="https://agentmods.dev/skills/panyuxin6/pyx-skills/simplify-codebase"><img src="https://agentmods.dev/badge/skills/panyuxin6/pyx-skills/simplify-codebase/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/skills/panyuxin6/pyx-skills/simplify-codebase"><img src="https://agentmods.dev/badge/skills/panyuxin6/pyx-skills/simplify-codebase.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 | $0.00164 | $0.01896 |
| Opus 5.5 | $0.00066 | $0.00758 |
| Sonnet 5.5 | $0.00033 | $0.00379 |
| Haiku 4.5 | $0.00016 | $0.00190 |
Grade A, and why
simplify-codebase 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 16d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
简化代码库
在不猜测产品意图的前提下,减少需要维护的 API、状态、配置、依赖及配套产物。以保留的行为契约和减少的维护义务判断价值,优先做少量已有证据支持的简化。
保持流程独立
让简化与代码审查保持独立。常规审查可将多余代码作为普通发现报告,不必加载本技能。只有明确要求简化,或观察到的候选项需要更广的使用者追踪时才使用。
不要为每次审查添加简化阶段,也不要把只读流程扩大成清理。没有修改权限,或另一个活跃流程要求目标保持不变时,选择 audit。保留无关的用户修改。
确定仓库契约
判断候选项前:
- 阅读适用仓库指令,并在可用时检查当前工作树状态。
- 找到与范围有关、由仓库维护的简化、防御模式、兼容性、生成文件、迁移、架构和决策记录。
- 检查清单、任务脚本、CI、分析器配置和测试配置,确认真实入口、排除项、生成范围和验证命令。
- 依赖已声明的路径、入口、所有者和命令前,确认它们仍存在。用观察到的地图定位证据,不要用它覆盖当前源代码或已确认契约。
语言约定、工具选择、覆盖策略、受保护范围和关卡命令由仓库决定。仓库规则可以要求更强保护,但不能授予修改权限,也不能降低全局高影响后果的等级。没有仓库策略时,保守推断并报告缺失边界。不要只因调用本技能就安装工具或创建策略文件。
选择操作和深度
选择一种操作和一种深度:
| 维度 | 模式 | 选择条件 |
|---|---|---|
| 操作 | audit |
用户要求查找、评估、调查或提出候选项;其他流程是只读;或修改权限不清楚。 |
| 操作 | apply |
用户明确要求在有界范围内修改或移除。 |
| 深度 | light |
范围是当前任务、当前变更或具名局部候选项,证明只需直接使用者和配套产物。 |
| 深度 | deep |
范围是子系统或仓库,或证明跨越包、动态加载、公开契约、持久化、线格式或生命周期归属。 |
对 light 完整阅读 轻量简化流程,对 deep 完整阅读 深入简化流程。不要为了完整性同时加载两者。
轻量工作若到达授权范围外的深入边界,停在有证据支持的建议。不要把大 diff 等同于深入工作,也不要把深入工作等同于必须暂停。
一次应用安全控制
任何 apply 前,完整阅读 分层安全控制,并将其作为唯一的修改权限依据。深入工作,或仓库分析器和聚合关卡重要时,也完整阅读 分层工具证据。
建立使用者证据
为每个看似相关的引用分类:
- 生产: 运行时入口、应用代码、加载器、注册表、配置、任务、随产品发布的示例和运行脚本。
- 非生产: 测试、文档、注释、快照、夹具、生成的预期结果和历史记录。
- 不明确: 反射、依赖注入、字符串分发、插件、生成代码、示例和条件构建输入。
- 外部或契约: 已发布 API、扩展点、持久化数据、线格式、迁移、CLI 行为和仓库外的使用者。
搜索符号、导出、文件名、事件名、配置键、包名、线协议字符串和注册路径。阅读调用点,不要只计数匹配。分析器只能发现候选项,绝不能证明不存在动态或外部使用者。
对字段、选项和状态变体,追踪完整效果链:谁产生值、经过哪些转换与转发、哪个实现支持它、最终产生什么可观察结果。到处传递或有测试覆盖,不代表功能实际生效;没有固定调用点,也不代表公开扩展点已无用途。
强候选项没有生产使用者、重复了别处拥有的事实、保留已被替代的路径,或承载没有当前所有者的通用性。只有测试和文档作为唯一使用者且它们不保护剩余行为时,才会增强候选项。孤立导入、格式、普通警告、风格偏好,以及没有使用者证据的复杂度属于正常开发,不属于本流程。
决定并行动
每个候选项只给出一种处理结论:
remove:证据支持在当前权限和范围内删除。keep:移除会破坏仍需保留的行为、契约或独立职责。defer:证据或授权不足,或需要先决定产品行为、迁移或重新设计。
存在生产调用方时,区分必须保留的行为与承载它的机制;重复状态或转发层仍可能在保留行为的前提下简化。若候选需要缩小产品能力,写清放弃什么、删掉什么及剩余义务,按 defer 报告,除非该候选及后果已获明确接受并满足分层安全控制。当前防御理由或兼容义务仍有效时保留;不要把测试或历史决定当作永久豁免,但在放弃其理由前需要更强的当前证据。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 16d ago Changed · +2 lines 2fbc82bd5fa5
- 1mo ago Changed · +40 tokens per session a56f614a36e8
- 2mo ago First seen · 80 lines · 124 tokens per session scan A 96b00abaf543
simplify-codebase is a skill published in the GitHub repository PANYUXIN6/pyx-skills (8 stars, last pushed 17d ago), licensed MIT. It adds 164 tokens to every session and 1,896 once invoked, about $0.0007 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 2026-08-31.
simplify-codebase compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| simplify-codebasePANYUXIN6/pyx-skills | Skill | 8 | 17d ago | MIT | A | 164 | Claude Code, Codex |
| autoreviewopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 48 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 945 | yesterday | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | 2d ago | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 70 | Claude Code |