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 michaelChe956/Cadence-skills --skill rule-configgit clone --depth 1 https://github.com/michaelChe956/Cadence-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/michaelche956/cadence-skills/rule-config)<a href="https://agentmods.dev/skills/michaelche956/cadence-skills/rule-config"><img src="https://agentmods.dev/badge/skills/michaelche956/cadence-skills/rule-config/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/michaelche956/cadence-skills/rule-config"><img src="https://agentmods.dev/badge/skills/michaelche956/cadence-skills/rule-config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 81 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium MCP Rug Pull · line 58 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 116 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00027 | $0.03720 |
| Opus 5 | $0.00014 | $0.01860 |
| Sonnet 5 | $0.00005 | $0.00744 |
| Haiku 4.5 | $0.00003 | $0.00372 |
Grade A, and why
rule-config 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 today.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code 与 Codex 规则配置
概述
配置 Claude Code 与 Codex 的规则:创建并维护 .claude/rules/ 下 7 个框架受管规则文件(模板携带共享 frontmatter 分桶:description/paths/agents/alwaysApply,Claude 消费 paths 条件加载、omp 消费索引与 rule:// 按需正文),内容 drift 时执行框架权威全覆盖;code-usage.md 按最终项目类型从 code-usage-coding.md / code-usage-noncoding.md 单选来源并以固定名称落地。流程还会将 CLAUDE.md 与 AGENTS.md 的 L0 受管区块升级到当前 v5(受支持旧版 v0~v4),创建 cadence/ 产物目录、迁移历史产物、保守合并 openspec/config.yaml,并按需配置 CodeGraph 与 Playwright;S11 omp 桥维护 .agents/rules/ 文件级软链集合与 .omp/AGENTS.md 受管活引用(语义见 references/merge-semantics.md §11.8);入口项目配置仅维护产物自动提交开关,不检测或写入技术栈。入口中的 ## 强制规则 不再以“缺失摘要行追加”为语义,而是执行强制规则章节规范化:创建、清理退役引用、按权威顺序重排并替换旧文案,同时保留无法识别的用户内容。所有需备份分支先将原文件复制归档到 cadence/legacy/<14位时间戳[-N]>/<相对项目根路径>,原位文件不动,再以 atomic_write 原子发布。
脚本报告始终提供不影响 overall 的顶层 warnings 数组;其实际 code 为 USER_LINES_KEPT、DUPLICATE_H2、ORPHAN_RULE6、INVALID_TOGGLE、L0_DEDUP、s9-settings-unsafe(settings.json 无法安全合并时保守跳过权限写入)、s9-allow-conflict(用户显式 allow 与受管 deny 冲突时保守跳过该 deny)、OMP_BRIDGE_USER_FILE_KEPT(.agents/rules/ 内用户文件保留/同名归档替换)、OMP_BRIDGE_MATERIALIZED(symlink 不可用降级物化副本),详情见 references/merge-semantics.md §11.3 与 §11.8。入口首个 ## 项目配置 章节还会确保唯一的“产物自动提交(design/plan/code)”开关:缺失时写入 关闭,合法用户值保留,非法值保留原文并报告 warning;既有技术栈等项目配置内容逐字保留,不由脚本检测或写入。Agent 读取时以 CLAUDE.md 为准、AGENTS.md 兜底;两者不一致按关闭处理并提示 ENTRY_TOGGLE_MISMATCH(这是读取层告警,不是脚本 warnings code)。
全部探测、非框架资产合并与受管文件写入由关联脚本 scripts/rule-config.py 以 dry-run / apply 两阶段完成;另有 verify 子命令执行只读五项自检,支持 --json 并以退出码 0/1 表示通过或发现漂移,适合在变更后核验并以报告为准;需要整体撤销权限区块时使用 --remove-permission-gate,详情均指向报告输出。框架受管规则文件绝不执行章节合并,也不生成“项目补充”或“原项目补充”。Agent 只负责定位脚本、按本文件编排调用、解读报告;当前系统无活跃冲突类型,两模式全程不经用户决策(决策文件机制休眠兜底,见 references/merge-semantics.md §11.6);不得由 Agent 自行读写目标项目的受管文件。合并与冲突处理的权威定义见 references/merge-semantics.md,本文件不重复其十张表。
参数模式
支持以下调用方式:
/rule-config
/rule-config no-interrupt
/rule-config --no-interrupt
- 等价规范化(强制):命令参数中的裸 token
no-interrupt与--no-interrupt完全等价,均进入 no-interrupt 模式;Agent 必须把裸 tokenno-interrupt规范化为脚本的--no-interrupt标志后再调用脚本,不得把裸 token 原样透传给脚本。 - 未携带上述 token:进入普通模式。
- 两种模式互斥;no-interrupt 的权威合并与禁迁移规则不得应用于普通模式。
What ships with it
27 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.
- references/merge-semantics.md 61 KB
- references/openspec/config.yaml 1.7 KB
- references/rules/agent-routing-kernel.md 2.5 KB
- references/rules/code-reading-coding.md 4.3 KB
- references/rules/code-reading-noncoding.md 2.3 KB
- references/rules/code-usage-coding.md 1.1 KB
- references/rules/code-usage-noncoding.md 1.0 KB
- references/rules/document-storage.md 7.3 KB
- references/rules/l0-history/agent-routing-kernel-v1.md 4.4 KB
- references/rules/l0-history/agent-routing-kernel-v2.md 5.1 KB
- references/rules/l0-history/agent-routing-kernel-v3.md 2.4 KB
- references/rules/l0-history/agent-routing-kernel-v4.md 2.5 KB
- references/rules/language.md 310 B
- references/rules/markdown-format.md 472 B
- references/rules/mcp-servers.md 13 KB
- references/rules/openspec-superpowers-workflow.md 3.7 KB
- references/rules/playwright.md 3.1 KB
- references/rules/README.md 3.1 KB
- scripts/rule-config.py 206 KB runs code
- tests/fixtures/entry-drift-claude.md 6.7 KB
- tests/fixtures/entry-kb-agents.md 11 KB
- tests/fixtures/invalidate-candidate.sh 151 B runs code
- tests/helpers/fake-codegraph.sh 1.4 KB runs code
- tests/helpers/run-script.sh 3.8 KB runs code
- tests/skill-clause-map.md 82 KB
- tests/test_rule_config.py 218 KB runs code
- tests/verify-managed-lifecycle.sh 96 KB runs code
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.
- today Changed a0cfcd6055d7
- yesterday Changed · +1 lines 1998a35f6c68
- 11d ago First seen · 127 lines · 27 tokens per session scan A 379f4ae13afa
rule-config is a skill published in the GitHub repository michaelChe956/Cadence-skills (11 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 3,720 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…