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 flanliulf/SpecLite --skill speclite-create-storygit clone --depth 1 https://github.com/flanliulf/SpecLiteWrote 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/flanliulf/speclite/speclite-create-story)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-create-story"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-create-story/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.
<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-create-story"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-create-story.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.01216 |
| Opus 5 | $0.00039 | $0.00608 |
| Sonnet 5 | $0.00016 | $0.00243 |
| Haiku 4.5 | $0.00008 | $0.00122 |
Grade A, and why
speclite-create-story 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.
What it actually says
[技能说明] # Create Story Workflow
**Goal:** 创建一份完整 Story 文件,让开发智能体获得无瑕实现所需的全部上下文。
**Your Role:** Story 上下文引擎,负责预防 LLM 开发者的错误、遗漏和实现灾难。
- 使用 `{communication_language}` 沟通,使用 `{document_output_language}` 生成文档。
- 不复制 epics,而是创建完整、优化过的 Story,让 DEV 智能体拥有实现所需的一切。
- 预防重复造轮子、用错库、放错位置、引入回归、忽视 UX、模糊实现、谎报完成、不汲取既有经验。
- 穷尽分析全部制品;可用时用研究子智能体、子进程或并行处理。
- 分析中的问题先保存,完整 Story 写完后统一提出;除初始选择或文档缺失外自动完成。
[核心能力]
- 配置与激活解析:解析三层 customize(base→team→user)和 workflow 块,加载 persistent_facts、config.toml、激活前置/后置步骤,以及 workflow.on_complete 终止指令。
- Story 目标发现与状态机维护:支持显式 story 标识或从 sprint-status.yaml 顺序发现首个 backlog Story,并维护 backlog/contexted → in-progress → done 的 Epic 状态机。
- 核心制品与历史情报分析:按发现协议加载 Epics、PRD、Architecture、UX、project-context、上一 Story 和最近 git 提交,提取业务目标、AC、依赖、经验、文件模式与测试方式。
- 架构护栏与 UPDATE 文件保护:提取技术栈、代码结构、API、Schema、安全、性能、测试、部署、集成模式,并为每个 UPDATE 文件记录“现状—本 Story 改什么—必须保留什么”。
- 最新技术研究:识别关键库、框架和 API,研究最新稳定版本、破坏性变更、安全更新、弃用信息、性能改进与当前最佳实践。
- 模板化 Story 生成:从 assets/story-template.md 初始化输出,并写入 Dependency Gate、Anchor Contract Map、Equivalent Implementation Policy、Evidence Plan 和 ready-for-dev Story 内容。
- 质量校验与 sprint 同步:用 references/checklist.md 自检生成结果,保存 Story,更新 sprint-status.yaml 中对应条目为 ready-for-dev,并保留原注释与结构。
[执行流程]
1. 先完整阅读 references/workflow-details.md;该文件是完整操作规约,不能跳过或缩写执行。
2. 激活时解析 workflow、三层 customize、workflow.persistent_facts 与运行项目根下的 merged runtime config;本 Skill 目录仅保留 config.toml.example 作为参考,具体命令、字段和合并规则见完整规约。
3. 按 references/discover-inputs.md 加载所有输入制品;对 sprint-status.yaml 必须从头到尾完整读取,以保留 Story 顺序。
4. 写入 Story 时,必须按完整规约列出的 template-output 段名顺序渲染,并把 Story 保存到 {implementation_artifacts}/stories/。
5. 收尾前用 references/checklist.md 校验并修复 Story,更新 sprint 状态,并执行完整规约中的 workflow.on_complete 终止指令。
[注意事项]
- 名称、目录与 YAML name 字段保持 kebab-case 一致:speclite-create-story。
- references/workflow-details.md 中的所有细节均为有效指令,不是背景材料;执行时必须完整遵循。
- 不得省略三层 customize、persistent_facts、config.toml 字段、Epic 状态机、上一 Story、git 情报、网络研究、UPDATE 文件三段式记录、Flow Gate 段、workflow.on_complete。
- Story 实现要求系统端到端继续工作;既有系统中维持功能正确所需的行为,即使未写入 AC,也必须视为需求。
- sprint-status.yaml 更新必须保留所有注释与结构,包含 STATUS DEFINITIONS,禁止覆写为缩略版。
- Story 文档末尾必须追加 *本文档由 speclite-create-story Skill 自动生成* 标注。
- 完成输出必须包含 Story ID、Story Key、文件路径、ready-for-dev 状态、dev-story、code-review-01-reviewer 和可选 Test Architect 护栏测试后续指引。
What ships with it
8 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 · 47 lines · 79 tokens per session scan A 9bdf28ae11a8
speclite-create-story is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 1,216 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 2026-09-03.
Other skills, from other repositories
intake
The planning front-door. Captures feature ideas and bugs as graded rows in the root INTAKE.md ledger. Use it when the user says "log an idea", "capture a bug", "add to the backlog", "note this down", "track this feature", or invokes /intake. Owns the requirements interview — fleshes out thin ideas, proactively…
msg
Root menu for msg skills, plus harness modes. --init is the one-time project bootstrap — use it when the user says "initialise project", "bootstrap repo", "set up the framework", "start a new project", or asks to set up project structure in an empty repo. Other modes: --init-staging (add a staging branch), --update…
Scaleway Naming And Tagging
Scaleway naming convention and mandatory tags — resource-type abbreviations, region codes, and owner/cost-center/environment/workload tags for cost attribution.
plan-em
Engineering Manager skill. Reads an approved PRD, runs pre-flight checks against AHA.md, GLOSSARY.md and ARCHITECTURE.md, auto-runs plan-review certification inline (no ask), identifies specialist agents to activate (roster approval — the single human gate), spins them up to write engineering sections directly into…
plan-review
Staff PM contract certifier. Reads an existing PRD and runs a fixed seven-check certification — each check tied to a named downstream consumer (regression authoring, pre-merge's PRD-consistency gate, the safety pauses, eng --build's row/ticket reads). Product tune (--product) runs checks 1/2/3/6; eng tune (--eng) runs…
Incident Management
Severity classification, runbook structure, and blameless postmortems — so incidents are handled calmly, restored fast, and learned from.