aisee:srs

aisee:srs is a skill for Claude Code, Codex from AISEE-LAB/aisee-plugin. It costs 159 tokens per session (2,430 once invoked), scanned A, original, MIT.

A structured conversation and documentation tool for creating a software requirements specification, or SRS. An SRS records users, goals, scope, workflows, rules, permissions, exceptions, and acceptance needs before technical design or coding.

In plain words
What is it for?
It is for clarifying requirements for apps, websites, back-end services, command-line tools, desktop software, and automated jobs. It can also compare a requested change with existing specifications and identify open questions.
Why use it?
It turns vague product ideas or existing-system requests into a shared description of what the software must do. This gives later planning and implementation work clearer boundaries.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions AGENTS.md.

Part of the aisee-plugin plugin — 14 skills shipped together

Good fit It is for clarifying requirements for apps, websites, back-end services, command-line tools, desktop software, and automated jobs. It can also compare a requested change with existing specifications and identify open questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aisee-lab/aisee-plugin/aisee-srs
Install

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.

Any agent
npx skills add AISEE-LAB/aisee-plugin --skill aisee-srs
Clone the repo
git clone --depth 1 https://github.com/AISEE-LAB/aisee-plugin

Made for: Claude Code, Codex.

Or install aisee-plugin, the plugin that ships this one along with the rest of its 14 skills.

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 aisee:srs

README.md
[![agentmods](https://agentmods.dev/badge/skills/aisee-lab/aisee-plugin/aisee-srs.svg)](https://agentmods.dev/skills/aisee-lab/aisee-plugin/aisee-srs)
Your own site
<a href="https://agentmods.dev/skills/aisee-lab/aisee-plugin/aisee-srs"><img src="https://agentmods.dev/badge/skills/aisee-lab/aisee-plugin/aisee-srs.svg" alt="Measured on agentmods" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,430 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 $0.00159 $0.02430
Opus 5 $0.00079 $0.01215
Sonnet 5 $0.00032 $0.00486
Haiku 4.5 $0.00016 $0.00243

Measured 8d ago against content hash 3cb3ffd54ff7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aisee:srs 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 8d 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.

plugins/aisee-plugin/skills/aisee-srs/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aisee:srs — OpenSpec 需求规格说明书

通过结构化对话挖掘软件需求,然后生成可交给 aisee:change-plan 使用,并可为后续 aisee:change-author 提供需求输入的需求规格说明书(SRS)。

生成或改写 planning doc 时,frontmatter 字段合同统一遵循 plugins/aisee-plugin/references/planning-doc-frontmatter.md;它只服务索引和追踪,不替代 OpenSpec 事实源。

当前主流程面向软件 / App / 后端 / CLI / Job 等场景。硬件、嵌入式和固件需求后续按专用流程整理;如果本次软件需求依赖设备,只记录软件可见的设备能力、状态、告警、操作环境、安全可靠性和验收约束,不展开硬件架构、固件设计或制造细节。

输入

用户提供以下任意一种输入:

  • 原始需求或功能想法(自由文本)
  • 模糊的产品目标或问题描述
  • 已有但尚未成型的需求草稿
  • 现有系统二次开发、改造、替换或兼容需求

可选参数:

  • --lang zh|en — 输出语言,默认 zh
  • --depth shallow|standard|deep — 对话深度,默认 standard
  • --baseline-aware — 基于现有 OpenSpec baseline specs、active changes 和既有需求文档识别新增 / 修改 / 移除 / 兼容行为。若项目中存在 openspec/specs/openspec/changes/aisee/docs/spec-migration/ 或历史 SRS,默认自动启用。

输出边界

aisee:srs 产出的是 规划级需求契约:它要足够详细,能支撑后续 change 边界规划和 change authoring;但它不是实现级接口设计、数据库设计、技术方案、逐页设计稿或设计系统。

必须覆盖:

  • 目标用户、业务目标、范围和非目标
  • 业务对象、业务状态、状态流转、业务流程和用户任务流
  • 功能需求、非功能需求、业务规则、权限规则和数据范围
  • 异常、失败、兼容、验收方向和待确认事项
  • 交付形态信号,例如 App、小程序、Web 管理后台、桌面 GUI、后端服务、CLI、导入导出、通知、异步处理
  • 现有项目二开时的新增 / 修改 / 移除 / 兼容行为,以及受影响 baseline 引用
  • 后续是否建议进入 aisee:change-plan,以及仍待确认的关键问题

可以记录但不得展开设计:

  • 页面相关的功能行为:必须采集或展示的数据字段、列表列、筛选条件、空状态、行操作、入口和完成后去向
  • 外部系统交互的业务目的、触发条件、成功/失败处理和数据含义
  • 设备参与的软件需求中,用户或系统可观察的设备能力、状态、告警、输入输出信号业务含义、安全可靠性和验收约束

禁止输出:

  • 视觉布局、间距、颜色、字体、图标、组件库选择或逐页线框图
  • API endpoint、数据库表字段、ORM、代码文件结构或迁移实现
  • 具体技术栈选择、服务拆分、队列方案、任务拆解或代码实现计划
  • 引脚表、寄存器表、RTOS 任务设计、驱动结构、BOM、PCB 布局、固件实现步骤或制造工艺
  • 未由用户或现有 baseline 确认的新增需求

如果用户需要接口、数据、任务或测试契约,应在 change artifacts 阶段处理,而不是在 SRS 中展开实现级设计。

ID 规则

aisee:srs 负责需求侧上游 ID:

  • FR:功能需求
  • NFR:非功能需求
  • RULE:业务规则
  • FLOW:业务流程或用户任务流,只有在 SRS 阶段已经明确时分配
  • STATE:业务状态或用户可感知状态,只有在 SRS 阶段已经明确时分配

正式写法只使用文档内编号,例如 FR-001NFR-001RULE-001FLOW-001STATE-001。跨文档来源交给后续 source-map.md 记录。不要为了满足模板创建无用编号、无用来源引用或 <!-- aisee:id ... -->

如果当前轮次还不能确定最终编号,可以使用 FR-NEW-001 一类临时占位符,并显式标注 [NUMBERING-FINALIZATION-REQUIRED]。SRS 不负责 API / DATA / TASK / TEST;这些由 change artifacts 承接。

Phase 0 — 读取项目上下文

Read the full file on GitHub · 131 lines

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. 8d ago First seen · 131 lines · 159 tokens per session scan A 3cb3ffd54ff7

Subscribe to this mod's changes

aisee:srs is a skill published in the GitHub repository AISEE-LAB/aisee-plugin (11 stars, last pushed 2mo ago), licensed MIT. It adds 159 tokens to every session and 2,430 once invoked, about $0.0008 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.