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 mileson/openprd --skill openprd-standardsgit clone --depth 1 https://github.com/mileson/openprdWrote 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/mileson/openprd/openprd-standards)<a href="https://agentmods.dev/skills/mileson/openprd/openprd-standards"><img src="https://agentmods.dev/badge/skills/mileson/openprd/openprd-standards.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Agent Snooping · line 28 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00048 | $0.01938 |
| Opus 5 | $0.00024 | $0.00969 |
| Sonnet 5 | $0.00010 | $0.00388 |
| Haiku 4.5 | $0.00005 | $0.00194 |
Grade A, and why
openprd-standards 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 4d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenPrd Standards
概览
当用户要求 OpenPrd 建立、维护、修复或解释项目文档标准时，使用这份 skill。它覆盖需求发现、change 生成、任务执行和发布就绪检查阶段的文档标准。
OpenPrd standards 管三件事：
docs/basic/下的项目基线文档.openprd/standards/file-manual-template.md定义的文件说明书规则.openprd/standards/folder-readme-template.md定义的文件夹 README 规则
研发期还包含一个轻量标准层：openprd dev-check <path> <file...> 或 node scripts/openprd-dev-check.mjs <path> <file...>，用于 Agent 在代码修改完成后、最终回复前回顾本轮 touched code files 的行数状态和下一步动作建议。它是 task-scoped advisory：只有拆分与当前目标同范围、风险不扩张且能保持行为不变时才可顺手处理；否则保留建议并把工作区规模债归入 workspaceAttention。它不强迫当前任务重构，也不要求用户回复模式开关。dev-check 同时检测本轮是否触达界面文件：最近 24 小时没有拼图证据板时输出视觉证据提醒，附建议命令与对话流嵌入提示。
自我成长标准层位于 .openprd/growth/：当 dev-check 高置信识别出新的代码扩展名时，可自动补齐识别规则并记录，减少后续重复提醒；执行中发现豁免路径、项目规矩、OpenPrd 默认行为或用户偏好需要增量时，保留来源标注候选。收工复盘时可运行 openprd grow . --review 生成后台 review，但不把候选变成当前任务的确认停顿。
维护 OpenPrd 本身时，新增或修改任何配置类能力都要检查是否应该成为 grow-aware 配置：高置信可复用、可被用户习惯影响、会随项目环境变化的配置默认纳入 openprd grow；不确定时主动询问用户；一次性固定规则才保留为静态配置。
唯一的基线路径就是 docs/basic/。
动手前
- 先读
skills/openprd-shared/SKILL.md - 从
.openprd/重建工作区状态 - 编辑前先检查 standards：
openprd standards <path> --verify
- 只有当用户要求初始化，或工作区正在初始化时，才补缺失 standards：
openprd standards <path> --init
必需基线文档
OpenPrd standards 要求以下文档存在：
docs/basic/file-structure.mddocs/basic/app-flow.mddocs/basic/prd.mddocs/basic/frontend-guidelines.mddocs/basic/backend-structure.mddocs/basic/tech-stack.md
如果涉及后端实现，docs/basic/backend-structure.md 必须显式覆盖 CLI 接入面和 API 接入面；如果某一面不适用，也要写明原因，而不是省略。
执行规则
openprd standards <path> --verify提供就绪证据；其发现不新增 OpenPrd 授权停顿，也不阻断用户已授权的当前动作- 代码修改完成后、最终回复前，针对本轮实际 touched code files 运行
openprd dev-check <path> <file...>；700 行以内正常，701-1500 行需留意，超过 1500 行说明后续改动成本较高。注意项只作为 task-scoped advisory；同范围、低风险时可顺手处理，其他规模债进入workspaceAttention，不扩大当前任务 - dev-check 或执行过程产生自我成长项时，区分处理：高置信工具识别补全可以自动固化；用户偏好、项目协作规矩和 OpenPrd 默认行为保留为来源标注候选，不打断当前任务
- 新增配置类能力时同步评审 grow-aware 入口：候选类型、scope、review/apply 行为、拒绝后不重复提示，以及 user-local 与项目共享配置的边界
- OpenPrd 自动生成的 change tasks 应包含 standards 维护任务
- 每次新增或修改源码文件，都要做 task-scoped 文档影响检查；检查本身不扩大实现范围
- 只有本轮代码变化直接使既有
docs/basic/、文件说明书或文件夹 README 失真时，才在后台同步相关文档；历史缺失、模板态或全局文档债记入workspaceAttention，不影响当前任务或已授权动作 - 如果涉及后端、脚本、Agent、工具链、服务或数据处理变更，必须把 CLI 与 API 视为同级接入面，更新
docs/basic/backend-structure.md中的命令入口、参数、输出契约、help/doctor/dry-run/status、接口协议和不适用说明 - 如果文档已经存在，检查本轮变更是否直接让它过期；只同步与当前改动对应的职责、流程、结构、依赖或产品行为，其他陈旧项记入
workspaceAttention README.md、README_EN.md、README_CN.md这类仓库入口文档也属于用户可见产物。更新功能定位、流程图、入口说明或示意图时，要优先用普通用户能理解的业务语言描述，并同步维护双语入口与成对图资产- 功能变更影响文件、文件夹、流程、架构、依赖或产品逻辑时，更新对应的
docs/basic/文档 - 功能变更影响代码文件职责时，更新对应文件说明书
- 功能变更影响文件夹职责或文件布局时，更新对应文件夹 README
- 如果最终不需要改文档，也要说明已经做过影响检查，以及为什么现有文档依然准确
- 更新
docs/basic/时禁止 append-only 堆叠：同一事实只保留一处最新版本，过时段落直接删除或改写，不要写“更新：/补充：”式追加；单行不要超过 300 字符，长内容拆成分点或小节 openprd standards <path> --verify会做文档质量体检：出现巨行（>300 字符）、平均行长退化（>200 字符）或prd.md落后超过 20 个 requirement 版本的警告时，先运行openprd docs-compact <path>查看按行号给出的压缩建议，压缩回填后再收口
What ships with it
1 file 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.
- 4d ago First seen · 83 lines · 48 tokens per session scan A 34e24e9c5def
openprd-standards is a skill published in the GitHub repository mileson/openprd (50 stars, last pushed 9d ago), licensed MIT. It adds 48 tokens to every session and 1,938 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 2026-09-03.
Other skills, from other repositories
openspec-bulk-archive-change
Archive multiple completed changes at once. Use when archiving several parallel changes.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
openspec-onboard
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
openspec-sync-specs
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
openspec-ff-change
Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.