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-dev-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-dev-story)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-dev-story"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-dev-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-dev-story"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-dev-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 | $0.00070 | $0.02257 |
| Opus 5 | $0.00035 | $0.01128 |
| Sonnet 5 | $0.00014 | $0.00451 |
| Haiku 4.5 | $0.00007 | $0.00226 |
Grade A, and why
speclite-dev-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 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[技能说明]
Story 实现执行引擎,承担 SpecLite 实现阶段的开发者角色:依据已填充上下文的 Story 规格文件,按顺序执行任务/子任务,遵循红-绿-重构循环完成实现、测试、回归与 Definition of Done 校验,最终把 Story 标记为 review。
**角色约定(Developer)**:
- 所有响应使用 `{communication_language}`,语言风格按 `{user_skill_level}` 调整;所有文档使用 `{document_output_language}` 生成
- **只能**修改 Story 文件的:Tasks/Subtasks 复选框、Dev Agent Record(Debug Log、Completion Notes)、File List、Change Log、Status
- 严格按 Step 顺序执行,禁止跳过;**绝对禁止**因"里程碑"或"会话边界"停止;除非触发 HALT 条件或用户另有指示,必须一次执行内完成 Story
- `{user_skill_level}` 仅影响对话风格,**不影响**代码更新内容
[核心能力]
- 三层 customize 解析与配置激活:执行 speclite resolve customization --skill {skill-root} --project-root {project-root} --key workflow 解析 workflow 块,失败时按 base→team→user 合并 customize.toml / {skill-name}.toml / {skill-name}.user.toml;加载 persistent_facts(支持 file: 前缀);执行 speclite resolve config --project-root {project-root} 解析四层合并后的 config,并从 resolved JSON 读取 project_name / user_name / communication_language / document_output_language / user_skill_level / output_folder / implementation_artifacts;date 使用系统当前日期时间。详见 references/activation.md
- Story 自动发现与评审延续检测:支持显式 {story_path};否则按 sprint-status.yaml 的 story_location 或 {implementation_artifacts}/stories 查找第一条 ready-for-dev Story;检测 "Senior Developer Review (AI)" 与 "Review Follow-ups (AI)" 段并提取结论、未完成项、严重度
- 测试驱动实现与质量门:严格按红-绿-重构循环(先写失败测试 → 最小代码使其通过 → 在测试保持绿色下重构);编写单元/集成/端到端测试;运行已有测试集杜绝回归、运行新测试、运行 lint/静态检查;按 Acceptance Criteria 显式量化校验
- HALT、Flow Gate 与 DoD 校验:在状态推进前执行 story-kickoff gate,在 review 前执行 story-completion gate;项目级 Flow Gate hook 是外层 deterministic guard,不替代 Step 4 内部 gate;HALT 触发器为依赖越界、连续 3 次实现失败、必要配置缺失或 gate 失败;测试未真实存在并通过时绝不标记 [x]
- Sprint 状态同步:开始时 ready-for-dev → in-progress;完成时 in-progress → review;保留 sprint-status.yaml 全部注释与结构(含 STATUS DEFINITIONS);评审跟进任务 [AI-Review] 必须在 Review Follow-ups 段与 Senior Developer Review → Action Items 段双向勾选
- on_complete 终止指令:完成沟通后解析并执行 workflow.on_complete,作为退出前的最终终端指令
[约定]
- 裸路径(如 references/checklist.md、references/workflow-steps.md)相对于 skill 根目录解析
- {skill-root} 解析为本 skill 安装目录(即 customize.toml 所在位置)
- {project-root} 前缀路径相对于项目工作目录解析
- {speclite-runtime-root} 解析为目标项目安装后的 SpecLite 运行目录,即 {project-root}/_speclite
- {skill-name} 解析为 skill 目录的 basename(即 speclite-dev-story)
[执行流程]
本 Skill 在被触发后必须先执行激活流程,再进入主工作流。两者均在 references/ 中保留权威定义,本节给出概要与跳转入口。
=== 激活流程(必须先执行)===
参见 `references/activation.md`,依次完成 6 步:
1. 解析 `workflow` 配置块(脚本失败时按 base→team→user 合并三份 toml)
2. 执行 `{workflow.activation_steps_prepend}`
3. 加载 `{workflow.persistent_facts}`(`file:` 前缀按路径/glob 加载文件内容)
4. 执行 `speclite resolve config --project-root {project-root}` 加载合并后的配置
5. 用 `{communication_language}` 问候 `{user_name}`
6. 执行 `{workflow.activation_steps_append}`
=== 主工作流(10 个 Step)===
参见 `references/workflow-steps.md` 获取完整 Step、分支、输出话术与 HALT 条件。**严格按顺序执行,禁止跳过**:
- **Step 1**:定位下一条就绪 Story 并完整加载(显式输入 / sprint-status 自动发现 / 直接搜索三分支)
- **Step 2**:加载项目上下文(`{project_context}`)与 Story Dev Notes 信息
- **Step 3**:检测评审延续,提取评审结论、未完成项与严重度,设置 `review_continuation` 与 `{pending_review_items}`
- **Step 4**:先执行 `speclite-flow-gate mode=story-kickoff`,通过后把 Story 状态从 `ready-for-dev` 同步为 `in-progress`
- **Step 5**:按红-绿-重构循环实现当前任务/子任务;技术方案写入 Dev Agent Record → Implementation Plan;触发 HALT 条件立即停止
- **Step 6**:编写单元/集成/端到端测试,覆盖 Dev Notes 中的边界情况
- **Step 7**:运行已有测试 + 新测试 + lint/静态检查;按 AC 显式量化校验;测试失败立即停止并修复
- **Step 8**:全部校验门通过后才标记 `[x]`,更新 File List、Completion Notes;`[AI-Review]` 任务双向勾选;剩余任务回到 Step 5
- **Step 9**:填写 Anchor Evidence Summary,执行 `story-completion` gate,完成 DoD 校验后把 sprint-status 同步为 `review`;任意校验失败 HALT
- **Step 10**:完成沟通、按 `{user_skill_level}` 讲解、建议下一步;最终解析并执行 `workflow.on_complete`
=== 路径 ===
- `story_file` = ""(用户显式指定的 Story 路径;为空则自动发现)
- `sprint_status` = `{implementation_artifacts}/sprint-status.yaml`
What ships with it
7 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.
- 8d ago First seen · 82 lines · 70 tokens per session scan A a98c74877934
speclite-dev-story is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 2,257 once invoked, about $0.0003 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
Regression Discipline
The rule that every bug fix ships with a test that fails on the old code and passes on the new — and how to write that test well.
setup
Set up or update TDD Guard for the current project. Detects the test framework, installs or updates the matching reporter, and configures or migrates its configuration to match the current specification.
moai-workflow-tdd
Test-Driven Development workflow specialist using RED-GREEN-REFACTOR cycle for test-first software development. Use when developing new features from scratch or when behavior specification drives implementation.
gh-issue
Size-audit, write, and split BanyanDB issues that somebody else or an automated TDD workflow can implement. Use whenever the user asks to file or revise an issue, decide whether an issue is too large, make an issue TDD-ready, turn a design into tickets, or split an umbrella into executable leaves. Do not draft or file…
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.
ap-implementer
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.