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.
git clone --depth 1 https://github.com/KtKID/x-dev-pipelinenpx agentmods add skills/ktkid/x-dev-pipeline/x-spec2Wrote 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/ktkid/x-dev-pipeline/x-spec2)<a href="https://agentmods.dev/skills/ktkid/x-dev-pipeline/x-spec2"><img src="https://agentmods.dev/badge/skills/ktkid/x-dev-pipeline/x-spec2.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 | $0.00126 | $0.01916 |
| Opus 5 | $0.00063 | $0.00958 |
| Sonnet 5 | $0.00025 | $0.00383 |
| Haiku 4.5 | $0.00013 | $0.00192 |
Grade A, and why
x-spec2 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 7d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
x-spec2
x-spec2 负责把系统意图建模成稳定需求与模块边界。task 拆解属于 x-req;x-spec2 通过准确的 Requirement、Scenario 和模块映射保护后续拆解方向。
产物
在 docs/spec/<spec-name>/ 中生成:
spec.md:必需。需求说明、原子用户要求追溯、判断依据、六元组覆盖、Requirement/Scenario 验收。modules.md:必需。模块职责、依赖、接口、风险、关键决策、状态及 Requirement 回指。design.md:按需。跨模块数据、状态、时序、资源或故障动态模型。
保持包内只有这 2+1 件。不要生成 README、task-map、diagram、task.md、tasks.md 或 dev-checklist;x-req 根据稳定 spec 拆 task。
模板位于 templates/。生成前完整读取对应模板,填充内容后删除 HTML 注释和占位符。
工作流
1. 收敛需求
从用户对话与仓库证据提取:
- 需求本质:用户真正要改变的系统结果。
- 范围:包含、排除、延后。
- 约束:技术、业务、兼容、权限、时间与运维边界。
- 不变量:任何实现都必须持续成立的规则。
- 用户原话:按单一意图拆成原子要求,保留原意;一句同时包含行为要求和结构指定时拆成两条 U。
- 验收:每条 Requirement 至少一个可判定 Scenario。
影响系统目标、范围或不变量的缺口需要先向用户确认。用户授权全权处理时,记录推断依据与待确认项后继续。
2. 调研现状
读取相关代码、文档、配置、日志与既有 spec,确认可复用模块、事实源、现有边界和约束。新项目可跳过代码复用调查。
3. 写 spec.md 并确认
使用 templates/spec.md:
- 每条原子用户要求分配唯一
U-ID并填写对应目标和包内落实锚点:行为型 U 回指唯一 Requirement;用户直接指定模块边界的结构型 U 回指 modules.md 中的模块。 - Requirement 名保持唯一;每条 Requirement 至少一个 Scenario。
- Scenario 包含 WHEN、THEN 与独立一行
验证: auto|manual;GIVEN 按需。 - Requirement 或关键决策需要用户原话之外的事实、外部规范、LLM 推断、暂定默认或待确认项时,按需拉出唯一
J-ID写入“判断依据”,并从消费位置引用。不要预枚举无消费者的 J。 - 每个 J 写明判断、来源类型、可定位证据或明确推断说明、确认状态;直接用户要求复用 U,不复制成 J。
- 六元组逐项填写有效的
文件#段落锚点或具体的不适用理由。 - 需求本质、系统目标、范围或不变量发生变化时,先让用户确认新的意图。
用户确认 spec.md 后再稳定模块设计,防止模块反向塑造需求。
4. 写 modules.md
使用 templates/modules.md。模块来自 Requirement 所需能力的聚合,每个模块至少回指一个 Requirement,每个 Requirement 至少被一个模块承接。
modules.md#关键决策 是 D-ID 的唯一真源。模块拆分、依赖方向、边界类、数据归属、协议或迁移存在合理备选,或选择会显著约束未来修改时,创建 D,记录最终选择、至少一个 U/J 依据、选择理由、真实备选与否决原因、重评条件。design.md 只消费 D,不定义 D。
模块总览的“决策回指”只使用:
U-ID:用户直接指定该模块边界,且该 U 的对应目标就是本模块。D-ID:模块拆分、依赖、边界类或数据归属由方案设计产生。
每个模块写清职责、依赖、边界类或对外契约、核心接口/数据、风险和状态。字段与当前需求无关时写简短理由,避免展开通用设计教材。
状态只使用:
- 探索中:目标或边界仍待确认。
- 方案确认:边界与验收已定,仍未开放给 x-req。
- 可进入 x-req:可以派生 task。
- 开发中:x-req 已派生 task 并进入实现。
- 已完成:派生 task 已完成验收。
处于探索中或方案确认的模块属于不稳定模块,交接时明确禁止进入 x-req。
5. 判断 design.md
出现以下任一动态关系时,使用 templates/design.md 生成 design.md:
- 数据跨模块产生、转换、传递或持久化。
- 实体具有多状态流转、状态所有者或恢复状态。
- 调用顺序、并发、重试、超时或事件先后影响结果。
- 资源具有生命周期、容量、配额、锁或释放责任。
- 依赖失败、部分失败、补偿、回滚或恢复路径影响结果。
What ships with it
3 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.
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.
- 7d ago First seen · 126 lines · 126 tokens per session scan A f3c5d93321c4
x-spec2 is a skill published in the GitHub repository KtKID/x-dev-pipeline (12 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 1,916 once invoked, about $0.0006 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
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
maintainer-preflight
Use before claiming work is done, before committing, and before opening a PR in this repo — runs the mcp-server test/typecheck/build gates and the committed-bundle rule. Trigger on "done", "ready to commit", "open a PR", or any completion claim.
repo-scope
Use when anyone asks what to work on next in this repo — "what's next", "anything left", "is there remaining work", "next task" — or before opening any PR the owner did not explicitly request. Enforces the docs/09 scope rule, whose default answer is: no work.
scope-lock
ALWAYS invoke before writing any code after a plan or spec is approved. Do NOT skip even if the plan is already in context. Triggers on: plan approval, spec approval, task kickoff, implementation start, '/scope-lock', 'set up the contract', 'lock scope'. Generates SCOPE.md boundary contract from the plan, enforces…
fable-discipline
Engineering discipline distilled from a forensic read of one model's work. Use when building a feature, fixing a bug, writing tests, hardening a data path, or running any task that spans multiple files, sources, or sessions. Two layers: how to RUN the task (stage it, verify each stage with a check that can fail, write…
product-analytics
Product analytics and growth expert. Use when designing event tracking, defining metrics, running A/B tests, or analyzing retention. Covers AARRR framework, funnel analysis, cohort analysis, and experimentation.