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-react-project-context-and-reviewgit 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-react-project-context-and-review)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-react-project-context-and-review"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-react-project-context-and-review/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-react-project-context-and-review"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-react-project-context-and-review.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 | $0.00104 | $0.00896 |
| Opus 5.5 | $0.00042 | $0.00358 |
| Sonnet 5.5 | $0.00021 | $0.00179 |
| Haiku 4.5 | $0.00010 | $0.00090 |
Grade A, and why
speclite-react-project-context-and-review 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 1mo 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
Speclite React Project Context And Review
[Overview(技能说明)]
Speclite React Project Context And Review 是 ecosystem-frontend-react module 的前端生态分析工作流。它面向已经选择 React ecosystem module 的目标项目,用代码事实、lockfile、配置文件、测试文件、官方文档或用户资料建立 React 项目上下文,并输出组件架构、state、routing、testing、accessibility、build 和 migration review 结论。
[Core Capabilities(核心能力)]
- 项目事实发现:读取 package.json、workspace 配置、lockfile、TypeScript / bundler / test 配置和源码入口,确认 React project 边界。
- 版本证据提取:React、React DOM、router、state library、test runner 和 build tool 版本必须来自 lockfile、package manager output、官方 docs 或用户提供资料。
- 组件架构审查:识别页面、route、feature、shared component、hook、context、server/client boundary 和 design-system usage。
- 状态与数据流审查:整理 local state、Context、Redux、Zustand、TanStack Query、Relay、Apollo 或其它状态/数据工具的实际使用证据。
- 路由与构建审查:基于证据分析 React Router、Next.js、Remix、Vite、Webpack、Turbopack 或 monorepo build wiring,不从依赖名臆测 runtime 行为。
- 测试与可访问性审查:检查 unit/component/e2e 测试、Testing Library、Vitest/Jest/Playwright/Cypress、ARIA 和 keyboard/focus 证据。
- 迁移风险记录:对 React major upgrade、router migration、state consolidation 或 framework migration 给出 evidence-linked risk list。
[Workflow(执行流程)]
详细步骤见 references/react-project-context-and-review-workflow.md。
1. 确认 `{project-root}` 与输出位置;若用户未给输出目录,先询问。
2. 收集 React evidence:manifest、lockfile、package manager output、framework config、source entry、test config、CI 和用户资料。
3. 只记录可验证事实。框架版本、API 语义和迁移建议不得来自记忆或猜测;缺证据时写入 `Unknowns(未知项)`。
4. 分析组件/route/state/testing/build/accessibility/migration 维度,并给出文件路径级证据。
5. 输出 Markdown review note 到用户指定位置,默认建议 `{project_knowledge}/frontend/react-project-context-and-review.md`。
[Notes(注意事项)]
- 本 Skill 只处理 React-specific 前端项目事实;通用 UX、PRD、Architecture、Story creation 和 Code Review 仍属于 sdlc workflow。
- 不要硬编码 React、React Router、Next.js、Vite 或测试框架的最新版本;必须从目标项目文件、lockfile、官方 docs 或用户资料取证。
- SpecLite 仍是 CLI + filesystem control plane;本 Skill 不创建 Web UI、dashboard、browser runtime 或 GUI product scope。
- 如果项目同时包含 Vue、Angular、Svelte 或 backend services,只分析与 React evidence 直接相关的范围,并把其它生态写为 out-of-scope。
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.
- 1mo ago First seen · 44 lines · 104 tokens per session scan A dcab89b623da
speclite-react-project-context-and-review is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 6d ago), licensed MIT. It adds 104 tokens to every session and 896 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-16.
Other skills, from other repositories
review-comments
Execute a feature-level review-comments cycle — aggregate unaddressed PR comments across every Feature.Repos PR, address or dismiss each one, and emit the standard handoff.
review-implementation-functionality-evidence
Implementation review Functionality/Evidence axis - audits plan satisfaction and verification evidence.
review-implementation-craft
Implementation review Craft axis - audits intrinsic code quality only.
review-implementation-cleanliness
Implementation review Cleanliness axis - audits change-set hygiene and pushability.
final-fix
Final-review fix pass that addresses requested changes and refreshes invalidated evidence.
idiomatic-go
Apply Go community idioms for API and package design, error and concurrency patterns, naming (initialisms, stutter, receivers), generics vs interfaces, and Go code review — including PR or diff review, questions about "the Go way", pointer vs value receivers, channels vs mutexes, and building Go language tooling…