speclite-story-review-01-reviewer

speclite-story-review-01-reviewer is a skill for Claude Code from flanliulf/SpecLite. It costs 84 tokens per session (2,390 once invoked), scanned A, original, MIT.

A read-only design review workflow that examines an Epic or Story from several independent angles. An Epic is a larger piece of work made up of smaller Stories.

In plain words
What is it for?
Use it to review one Story or a group of Stories, classify findings, and save a numbered design review report.
Why use it?
It finds missing details, contradictions, and unclear boundaries before development begins.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it to review one Story or a group of Stories, classify findings, and save a numbered design review report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flanliulf/speclite/speclite-story-review-01-reviewer
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 flanliulf/SpecLite --skill speclite-story-review-01-reviewer
Clone the repo
git clone --depth 1 https://github.com/flanliulf/SpecLite

Made for: Claude Code.

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 speclite-story-review-01-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-story-review-01-reviewer/github.svg)](https://agentmods.dev/skills/flanliulf/speclite/speclite-story-review-01-reviewer)
Your own site
<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-story-review-01-reviewer"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-story-review-01-reviewer/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 speclite-story-review-01-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-story-review-01-reviewer"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-story-review-01-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,390 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 $0.00084 $0.02390
Opus 5 $0.00042 $0.01195
Sonnet 5 $0.00017 $0.00478
Haiku 4.5 $0.00008 $0.00239

Measured 8d ago against content hash e7ba0116c6b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

speclite-story-review-01-reviewer 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.

assets/source/speclite/sdlc-skills/3-solutioning/speclite-story-review-01-reviewer/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[技能说明] 针对指定 Epic 或单个 Story 执行设计文档审查(SR),通过并行三层对抗式审查(Structure & Completeness Hunter、Consistency Checker、Contract & Boundary Auditor)对 Story 设计文档进行多维度分析,将发现进行四桶分类和严重性标签映射后,输出结构化的审查总结并保存到规范化的结果文件中。支持 Epic 粒度和 Story 粒度的双模式审查,以及多轮审查的自动编号和历史记录追踪。

[核心能力] - 并行三层审查:通过 Agent 工具同时启动 Structure & Completeness Hunter、Consistency Checker、Contract & Boundary Auditor 三个独立子代理,从结构完整性、跨文档一致性、契约边界三个正交维度并行分析,天然实现上下文隔离 - 双粒度审查:支持 Epic 模式(审查 Epic 下全部 Story,启用跨 Story 维度)和 Story 模式(审查单个 Story,跳过 Story 间冲突维度),根据用户输入自动判定 - 四桶分类:将所有发现去重后分入 decision_needed / patch / defer / dismiss 四个桶,每个桶有明确的判定条件 - 严重性标签映射:四桶分类与 [高/中/低] 严重性标签并存,基于来源数量和安全关键词进行映射 - Flow Gate 设计审计:Contract & Boundary Auditor 检查 Story 是否把 guidance path、建议文件名或历史实现形态误写成 hard gate - 自动轮次检测:自动扫描已有审查结果文件,确定当前轮次编号 - 首轮/复审自适应:首轮审查聚焦全量文档,复审聚焦上轮修复点和残留问题 - 大批量分批处理:Epic 模式下 Story > 5 时自动分批(每批 ≤ 5 个),确保审查质量 - 子审查失败降级:任一子代理失败时使用剩余层继续;全部失败时降级为单一 LLM 审查 - 只读安全保障:严格禁止修改 Story 文档和源码,仅输出审查总结

[执行流程]

路径约定和文件名格式以 `references/sr-config.md` 为准。
运行时变量使用 `$snake_case` 格式标识,与 sr-config.md 中的文件名模板占位符 `{花括号}` 区分。

Step 1:判定审查粒度并定位目录
    - 接收用户指定的审查目标(Epic 标识或 Story 标识)
    - 读取 `references/sr-config.md` 获取路径约定和双粒度判定规则
    - 根据用户输入判定 `$review_scope`:
        - 匹配 `epic {N}` / `epic-{N}` → `$review_scope = "epic"`,`$epic_id = N`
        - 匹配 `story {N-M}` / `{N-M}` / Story 文件路径 → `$review_scope = "story"`,`$story_id = N-M`,从前缀提取 `$epic_id`
    - 按 `$review_scope` 和配置中的目录格式确定 `$sr_dir`
    - 创建临时文件目录:`$sr_dir/.tmp/`(如不存在)

Step 2:检测审查轮次
    - 读取 `references/sr-config.md` 获取审查总结文件名格式
    - 按配置中的轮次检测规则,扫描 `$sr_dir` 下已有的审查总结文件
    - 统计已有轮次数量,确定本轮轮次号 → `$round_number` = 已有轮次 + 1
    - 判断审查类型 → `$review_type`:
        - `$round_number` == 1 → 首轮审查
        - `$round_number` > 1 → 复审(需参考历史记录)

Step 3:收集审查上下文
    - IF 复审(`$round_number` > 1):
        - 读取历次 SR 结果文件(按配置中的文件名格式匹配)
        - 读取历次评估文件(按配置中的文件名格式匹配)
        - 重点关注最新一轮评估文件中的 "## 修订执行记录" 章节
        - 建立"已修复问题清单" → 写入 `$sr_dir/.tmp/review-context.md`
    - 读取 Epic 定义文件:按配置中的 Epic 文件目录定位 `epic-{$epic_id}.md`
    - IF Epic 模式:
        - 按配置中的 Story 匹配规则扫描该 Epic 下全部 Story 文件 → `$story_files`
        - 统计 Story 数量
    - IF Story 模式:
        - 按配置中的 Story 匹配规则定位指定 Story 文件 → `$story_files`
    - 确定对照基准文件清单 → `$baseline_files`:
        - 必需:`project-context.md`
        - 必需:`epic-{$epic_id}.md`
        - 按需:架构文档(`03-core-decisions.md`、`04-implementation-patterns.md`)
        - 按需:owning SPEC(当 Story 声称固定源码路径、schema、fixture 或 command 为 hard gate 时必须读取)
        - 按需:前序 Epic 的相关 Story(当本 Epic 引用了前序 Epic 接口时)
    - 若 Epic 文件不存在:终止执行,告知用户

Step 4:执行 Story 审查(三层并行审查引擎)
    - 传入 review-engine.md 的变量:
        - `$review_scope`、`$epic_id`、`$story_id`、`$sr_dir`、`$round_number`、`$review_type`
        - `$story_files`、`$epic_file`、`$baseline_files`
    - 传入 review-engine.md 的文件(复审时):
        - `$sr_dir/.tmp/review-context.md`
    - 读取并执行 `references/review-engine.md`
    - 该引擎将完成:构建审查输入 → 并行三层审查 → 规范化去重 → 四桶分类 + 严重性标签映射
    - 引擎执行完毕后获取:
        - `$failed_layers`(上下文传回,失败的审查层名称列表)
        - `$review_findings`(从 `$sr_dir/.tmp/classified-findings.json` 读取)

Step 5:生成并保存审查总结
    - 读取 `$sr_dir/.tmp/classified-findings.json` 获取 `$review_findings`
    - 读取输出格式模板:`assets/output-template.md`
    - 根据 `$review_scope`(epic/story)和 `$review_type`(首轮/复审)选择对应模板变体
    - 将 `$review_findings` 整理为结构化总结
    - 只保存总结/结论部分,不保存完整审查过程
    - 确定今天日期,格式为 YYYYMMDD
    - 创建 `$sr_dir` 目录(如不存在)
    - 按 `references/sr-config.md` 中的文件名格式保存文件
    - 严格按照模板中定义的章节结构和格式规范输出,包括:
        - YAML 元信息头部(含 Scope 字段)
        - 审查结论(含审查层状态标注,引用 `$failed_layers`)
        - 审查范围
        - 上轮问题回顾(复审时)
        - 新发现(含严重性标签、四桶分类、审查来源、证据、影响、建议)
        - 逐篇审查结论(仅 Epic 模式)
        - 通过项(含 defer 桶的已知既有问题)
    - 清理临时文件:删除 `$sr_dir/.tmp/` 目录及其所有内容(删除失败不阻断流程)
    - 向用户展示审查总结要点
    - 完成后返回:"✅ SR Story 设计审查完成(第 `$round_number` 轮),结果已保存"

Read the full file on GitHub · 120 lines

Files

What ships with it

4 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.

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 · 120 lines · 84 tokens per session scan A e7ba0116c6b6

Subscribe to this mod's changes

speclite-story-review-01-reviewer is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 2,390 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.