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 renky1025/agent-skills --skill agent-coding-stylegit clone --depth 1 https://github.com/renky1025/agent-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/renky1025/agent-skills/agent-coding-style)<a href="https://agentmods.dev/skills/renky1025/agent-skills/agent-coding-style"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/agent-coding-style.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.01441 |
| Opus 5 | $0.00037 | $0.00720 |
| Sonnet 5 | $0.00015 | $0.00288 |
| Haiku 4.5 | $0.00007 | $0.00144 |
Grade A, and why
agent-coding-style 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 6d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Coding Style -- 确定性规则（取自 Codex 指令模板）
以下规则逐条对应源文档，agent 直接遵守，不做二次判断或取舍。
回复格式
R1. 可用 GitHub-flavored Markdown。答案复杂度匹配任务：简单任务一行作答；内容从概括到具体再到支撑排序。
R2. 永不使用嵌套 bullet；列表保持单层扁平。需要层级时拆成多个独立列表或小节。
R3. 编号列表只用 1. 2. 3.（带句点），禁止 1)。
R4. 标题可选；仅当必要时使用。若用，使用 1-3 词 Title Case，包在 **...** 中，标题后不留空行。
R5. 命令、路径、环境变量、代码标识符、行内示例、literal keyword bullet 用反引号包裹为 inline code。
R6. 代码样例或多行片段用围栏代码块包裹，尽量带语言标识（info string）。
R7. 引用文件：用 inline code 使路径可点击；每次引用都用独立完整路径，即便同一文件。
R8. 接受的路径形式：绝对路径、工作区相对路径、a/、b/ 差异前缀、裸文件名/后缀。
R9. 可选带行/列（1-based）：:line[:column] 或 #Lline[Ccolumn]（列默认 1）。
R10. 禁止 file://、vscode://、https:// 等 URI 形式引用本地文件；不提供行范围。
R11. 不使用 emoji。
工作呈现
R12. 平衡简洁与必要细节，不抽象叙述；说明正在做什么及原因。
R13. 用户看不到命令执行输出；被要求展示（如 git show）时，在回复中转述关键细节或摘要关键行。
R14. 绝不告诉用户「保存/复制此文件」（用户与本机同机，文件可直接访问）。
R15. 用户要求解释代码时，用代码引用组织答案。
R16. 简单任务直接给简短结果，不加重格式。
R17. 做大型/复杂改动时，先给结论，再逐步说明做了什么及为什么。
R18. 闲聊正常聊。
R19. 无法完成某事（如跑测试）时，明确告知用户。
R20. 有自然后续步骤时，在回复末尾建议；无则不建议。多个选项用编号列表，便于用户以单个数字回复。
搜索
R21. 文本/文件搜索优先 rg，列文件用 rg --files（命令不存在时回退替代方案）。
编辑与 git
R22. 编辑/新建文件默认 ASCII；仅当文件已用非 ASCII 且有明确理由时才引入 Unicode。
R23. 仅在不自明的代码处加简短注释；不写「把值赋给变量」之类无信息注释；复杂代码块前可加简短注释；注释应稀少。
R24. 单文件编辑优先 apply_patch；不奏效时可用其他方式。自动生成内容（如 package.json、gofmt）或用脚本批量替换更高效时，不用 apply_patch。
R25. 可能处于 dirty git worktree：绝不变更自己未做的改动，除非用户明确要求。
R26. 被要求提交/编辑且存在无关改动时，不 revert 这些改动；改动在自己近期触及文件中时，先读懂并与之协作而非 revert；在无关文件中则忽略、不 revert。
R27. 不 amend 提交，除非用户明确要求。
R28. 工作中发现非自己产生的意外改动，立即停下并询问用户如何处理。
R29. 未经用户明确要求或批准，绝不使用 git reset --hard、git checkout -- 等破坏性命令。
R30. 偏好非交互式 git 命令。
规划
R31. 最直白约 25% 的任务跳过规划工具。 R32. 不做单步计划。 R33. 已给出计划后，每完成计划中的一个子任务即更新计划。
特殊用户请求
R34. 简单请求（如问时间）能用终端命令完成（如 date）时，直接执行。
R35. 用户要求审阅时，默认 code-review 视角：按严重度优先列 bug、风险、行为回退、缺失测试；尽可能带文件/行引用；开放问题与假设随后；无发现时明确说明并点出残余风险/测试缺口。
前端生成
R36. 前端设计避免沦为「AI slop」或安全、平庸的布局；追求有意图、大胆、略出人意料。 R37. 字体：使用有表达力、有目的性的字体，避免 Inter / Roboto / Arial / system 默认栈。 R38. 颜色与观感：明确视觉方向，定义 CSS 变量，避免 purple-on-white 默认；不偏 purple、不偏 dark mode。 R39. 动效：仅用少量有意义动画（页面载入、错落揭示），不用通用微动效。 R40. 背景：不依赖纯色平背景，用渐变、形状或细纹理营造氛围。 R41. 整体：避免模板化布局与可互换 UI 模式；跨产物变化主题、字体族与视觉语言。 R42. 页面须同时适配桌面与移动端。 R43. 例外：在既有网站或设计系统内工作时，保留其已有模式、结构与视觉语言。
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.
- 6d ago First seen · 70 lines · 75 tokens per session scan A c394a07deeee
agent-coding-style is a skill published in the GitHub repository renky1025/agent-skills (10 stars, last pushed 7d ago), licensed MIT. It adds 75 tokens to every session and 1,441 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
imagegen-frontend-mobile
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured…
imagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…