manage-prd-docs

manage-prd-docs is a skill for Codex from bosens-China/tc39-atlas. It costs 132 tokens per session (4,026 once invoked), scanned A, original, MIT.

A workflow for managing product requirements across documents for current decisions, future plans, and active implementation. A product requirement describes what a product should do and how success will be checked.

In plain words
What is it for?
Use it to record clarified requirements, maintain PRDs and plans, track work in progress, update documentation during implementation, and close completed requirement work.
Why use it?
It keeps each requirement in one appropriate documentation stage and avoids conflicting copies. It also synchronises requirements with implementation work and related task lists.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md; $skill-name invocation.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is - [团队权限 v2](./plans/team-permissions-v2/PRD.md).

Good fit Use it to record clarified requirements, maintain PRDs and plans, track work in progress, update documentation during implementation, and close completed requirement work.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/bosens-China/tc39-atlas
agentmods
npx agentmods add skills/bosens-china/tc39-atlas/manage-prd-docs

Made for: Codex.

Wrote 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.

agentmods badge for manage-prd-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/bosens-china/tc39-atlas/manage-prd-docs/github.svg)](https://agentmods.dev/skills/bosens-china/tc39-atlas/manage-prd-docs)
Your own site
<a href="https://agentmods.dev/skills/bosens-china/tc39-atlas/manage-prd-docs"><img src="https://agentmods.dev/badge/skills/bosens-china/tc39-atlas/manage-prd-docs/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.

agentmods 80×15 button for manage-prd-docs

Your own site · 80×15
<a href="https://agentmods.dev/skills/bosens-china/tc39-atlas/manage-prd-docs"><img src="https://agentmods.dev/badge/skills/bosens-china/tc39-atlas/manage-prd-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,026 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00132 $0.04026
Opus 5 $0.00066 $0.02013
Sonnet 5 $0.00026 $0.00805
Haiku 4.5 $0.00013 $0.00403

Measured 11d ago against content hash 9d8da969b89f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

manage-prd-docs 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 11d 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.

.agents/skills/manage-prd-docs/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manage PRD Docs

围绕产品需求进行讨论,把已生效、未来已成型和正在实施的产品决策放在不同生命周期层,并保持单一权威来源。

自动推进需求生命周期

  • 检测到用户在讨论、澄清、变更、计划、实现或完成产品需求时,立即进入本工作流,不要等待用户说“讨论需求”“落盘”或“合并 PRD”。
  • 先判断需求是否成型:目标、范围、核心需求和可验证的验收标准已经明确,且不存在会改变产品或实施方向的关键未决项。
  • 需求未成型时继续讨论,只询问对方向有实质影响的问题;不为低风险细节阻塞推进。
  • 需求成型后立即按状态落盘:已生效的行为更新现行 PRD;未开始实施的未来需求进入 docs/plans/;已开始或本轮同时要求实现的需求进入 docs/work/。不再请求额外落盘授权。
  • 只写入已经明确的当前结论;尚在比较的方案、随口设想和无法判断是否确认的内容暂不写入。
  • 实现过程中持续同步 PRD 和 Todo。当本轮需求的实现、验证和必要文档全部完成时,主动收口,不等待用户再说“合并 PRD”。
  • 把纯讨论或 PRD 编写任务的结束与实现完成区分开:未开始的成型需求保留在 docs/plans/;部分实现、验证失败、存在阻塞或仍有未决项时保留在 docs/work/
  • 只自动删除本轮已完成需求对应的精确工作目录。迁移或删除旧 Phase、历史 PRD 和其他非本轮临时文档前,仍取得用户明确授权。

识别文档约定

  1. 定位仓库根目录,先读取适用的 AGENTS.md 和仓库级说明。
  2. 默认使用根目录下的 docs/,优先遵循仓库已有的文档入口和命名约定。
  3. 如果存在 docs/index.md,先按索引定位现行 PRD、未来计划、进行中需求和其他权威文档。
  4. 读取相关 PRD、上下游计划、Todo、用户文档、README 和代码契约,避免建立重复或冲突的权威来源。
  5. 增量修改并保留无关的人工内容。

使用三层文档

把文档分成现行、未来计划和进行中三层:

docs/
├── index.md                 # 稳定的文档类别与生命周期导航
├── PRD.md                   # 现行产品决策与跨主题边界
├── prd/                     # 按稳定产品模块拆分的现行 PRD
│   └── <topic>.md
├── plans/                   # 已成型但尚未开始的未来需求
│   └── <requirement>/
│       ├── PRD.md
│       └── prd/             # 计划 PRD 需按主题拆分时使用
│           └── <topic>.md
└── work/                    # 仅在存在进行中需求时使用
    └── <feature-name>/
        ├── PRD.md
        ├── TODO.md
        └── prd/             # 当前需求 PRD 过长时按主题拆分
            └── <topic>.md
  • 不创建空目录。
  • 把已经生效的行为或稳定承诺写入现行 PRD,把未开始的成型需求写入 docs/plans/,把正在实施的需求写入 docs/work/
  • 全新产品尚未形成现行能力时,未开始实施就使用 docs/plans/initial-release/,已开始实施就使用 docs/work/initial-release/,不要为了结构完整创建空的 docs/PRD.md
  • 版本对用户或产品确实有意义时,允许在 plans/work/ 使用 <requirement>-v2 等名称;完成后不把版本目录保留为永久历史档案。
  • 只有能独立排期、验收、延期或取消的 v2、v3 才分开维护;仅为开发顺序服务的 Phase 留在同一进行中 PRD 和 Todo 中。
  • 允许在进行中 PRD 或 Todo 内规划实施阶段,但完成后不保留阶段档案。
  • 不强制创建发布文档、用户文档或其他项目特有文件;已有时维护链接和一致性。

维护现行 PRD

docs/PRD.md 视为产品当前有效决策的唯一入口。在根 PRD 保留产品级范围、跨模块行为、统一术语、全局边界和模块导航;把稳定产品模块的详细当前决策放在 docs/prd/<module>.md

每个主题只保留:

## 翻译存储与人工覆盖

- 当前决策:……
- 为什么:……
- 边界 / 非目标:……
- 权威入口:链接到用户文档、README 或源码契约。

Read the full file on GitHub · 254 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 254 lines · 132 tokens per session scan A 9d8da969b89f

Subscribe to this mod's changes

manage-prd-docs is a skill published in the GitHub repository bosens-China/tc39-atlas (0 stars, last pushed today), licensed MIT. It adds 132 tokens to every session and 4,026 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

create-pr

Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.

prisma/orm · 48 tokens

triage-contributor-pr

Triage open pull requests from external contributors to prisma/prisma and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…

prisma/orm · 131 tokens

contrib-pr

Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.

prisma/orm · 65 tokens

github-review-iteration

Orchestrates a GitHub PR review loop by delegating triage and implementation to dedicated sub-agents, then repeating until actionable review items are cleared. Use when the user says “address PR review”, “triage review comments”, or “iterate until review is clean”.

prisma/orm · 60 tokens

publish-npm-version

Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump to ". When the maintainer merges the PR, the Publish to npm workflow runs automatically and ships the new version to npm…

prisma/orm · 159 tokens

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens