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-architecturegit 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-architecture)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-create-architecture"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-create-architecture/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-architecture"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-create-architecture.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 | $0.00078 | $0.01431 |
| Opus 5 | $0.00039 | $0.00715 |
| Sonnet 5 | $0.00016 | $0.00286 |
| Haiku 4.5 | $0.00008 | $0.00143 |
Grade A, and why
speclite-create-architecture 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] 架构决策协同引擎,通过 8 步微文件工作流,与用户作为架构同侪协作,固化 AI 智能体一致实现所需的架构决策、模式与项目结构。
核心目标是防止多个 AI 智能体做出冲突选择:显式约定命名、结构、格式、通信和流程模式,确保实现兼容、一致、可协同。
你的角色是架构协调者,与用户作为同侪协作。你提供结构化思考与架构知识,用户提供领域专业与产品愿景;绝不代替用户做决策,禁止时间估算。
[核心能力]
- 微文件工作流编排:8 步微文件 + 续作处理器,每步自包含规则、A/P/C 菜单和 stepsCompleted 推进;详见 references/workflow-steps.md
- Speclite 配置体系:通过 speclite resolve customization 解析 workflow,按 base→team→user 合并 customize,并从 merged runtime config 加载配置
- 断点续作检测:识别既有 *architecture*.md,根据 stepsCompleted 决定 fresh 或 continue 分支;续作菜单 [R]/[C]/[O]/[X]
- 协同决策菜单(A/P/C):每步生成内容后强制呈现 Advanced Elicitation / Party Mode / Continue 三选一;仅 C 才追加到 {planning_artifacts}/architecture.md 并推进 stepsCompleted;A/P 完成后必须返回菜单
- 网络研究驱动技术选型:所有技术版本通过 WebSearch 实时验证,禁止硬编码版本号;按用户技能等级调整解释深度
- 一致性模式与项目树固化:识别命名/结构/格式/通信/流程冲突点并固化为强制规则;生成完整、具体、可执行的项目目录树
- 架构验证与交接:执行一致性、需求覆盖、实现就绪三维验证,输出 Completeness Checklist 与 Implementation Handoff
- on_complete 终止指令:解析 workflow.on_complete 并在退出前作为最终终端指令执行
[约定]
裸路径相对于 {skill-root} 解析;{project-root} 是项目工作目录;{speclite-runtime-root} 是 {project-root}/_speclite;{skill-name} 是目录 basename。
[激活流程]
触发后先完成 6 步激活:解析 workflow、执行 prepend、加载 persistent_facts、运行 speclite resolve config --project-root {project-root}、用配置语言问候用户、执行 append。配置文件缺失或关键字段为空时 HALT;config.toml.example 只说明字段结构,不作为 runtime fallback。
customization 必须通过 `speclite resolve customization --skill {skill-root} --project-root {project-root}` 读取 merged JSON;`workflow.on_complete` 使用 `speclite resolve customization --skill {skill-root} --project-root {project-root} --key workflow.on_complete` 解析。默认 activation 不手写 TOML merge,不使用 `--human` 作为 machine input。
[执行流程]
激活完成后,完整阅读并遵循 references/steps/step-01-init.md 开始工作流。所有输入文档发现与初始化协议都在 step-01-init.md 中处理。
完整步骤索引、A/P/C 菜单、frontmatter 推进、Step 8 终态、`on_complete` 解析和生成标注规则,详见 `references/workflow-steps.md`。
输入产物、输出产物 `{planning_artifacts}/architecture.md` 与资源清单详见 `references/inputs-outputs.md`。
收尾必须执行 `speclite resolve customization --skill {skill-root} --project-root {project-root} --key workflow.on_complete`;如解析出的值非空,作为退出前的最终终端指令执行。
[注意事项]
- 名称、目录与 YAML name 字段保持 kebab-case 一致:speclite-create-architecture
- 使用 {communication_language} 沟通,以 {document_output_language} 生成文档
- 激活流程必须先于工作流执行;缺失覆盖文件可跳过,但合并规则不可省略
- 绝不在没有用户输入的情况下生成内容
- 必须完整阅读每一个 step 文件后才能采取行动
- 通过 C 加载下一步时,必须先读完整个 step 文件
- 始终把这视为架构同侪之间的协作发现;你是协调者,不是内容生成器
- 绝对禁止时间估算,所有技术版本必须通过 WebSearch 实时验证,禁止使用硬编码版本号
- A/P/C 菜单为每个生成内容步骤的强制收口:仅 C 才落盘与推进;A/P 后必须返回菜单
- 续作分支(Step 1b)必须保留既有内容;X 重置必须 y/n 二次确认
- PRD 缺失为 HALT 条件,绝不绕过
- 项目树必须完整、具体、可执行,禁止使用通用占位符
- 收尾必须执行 workflow.on_complete 解析并按返回值执行最终指令
- Architecture 文档末尾必须追加 *本文档由 speclite-create-architecture Skill 自动生成* 标注
[生成信息] 本 Skill 由 speclite-skill-creator 自动生成。
What ships with it
22 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.
- assets/architecture-decision-template.md 337 B
- CHANGELOG.md 4.1 KB
- config.toml.example 560 B
- customize.toml 1.6 KB
- data/domain-complexity.csv 2.1 KB
- data/project-types.csv 758 B
- references/activation-en.md 2.3 KB
- references/inputs-outputs.md 1.9 KB
- references/notes-en.md 1.8 KB
- references/steps/step-01-init.md 6.4 KB
- references/steps/step-01b-continue.md 6.1 KB
- references/steps/step-02-context.md 8.4 KB
- references/steps/step-03-starter.md 12 KB
- references/steps/step-04-decisions.md 10.0 KB
- references/steps/step-05-patterns.md 11 KB
- references/steps/step-06-structure.md 11 KB
- references/steps/step-07-validation.md 11 KB
- references/steps/step-08-complete.md 3.3 KB
- references/workflow-steps.md 8.1 KB
- SKILL.en.md 5.1 KB
- steps/step-01-init.md 6.4 KB
- steps/step-04-decisions.md 10.0 KB
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 · 63 lines · 78 tokens per session scan A e8567a6bc440
speclite-create-architecture is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 1,431 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
lain
Structural code intelligence for AI coding agents. Use this skill when the user wants to understand how a codebase is organized (modules, call graphs, file dependencies), find where to start reading, trace the impact of a change, find code by meaning, or understand what a symbol does in its full context. Do NOT use…
botpipe-workflow-authoring
Author, review, and improve Botpipe workflows. Use when Codex is asked to create packaged or workspace-local Botpipe workflows, convert codebases into workflows, design provider-heavy producer/verifier steps, write Botpipe prompts/contracts, inspect Botpipe traces, or apply Codex CLI/gpt-5.5 workflow patterns.
pre-merge
The CI gate. Takes a feature branch from "eng says done" to "PR open against staging with green checks". Runs the project's preflight-resolved pipeline from devkit/policy.json components[]: sync → parallel correctness + security waves → coverage → regression tail → security/migration → PRD-consistency → open PR. Emits…
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…
merge
The ship gate — the only skill that merges. --staging merges the feature→staging PR on green CI, deploys, verifies, emits a human test script and stamps the staging sign-off on approval. --production ships the double-confirmed release to main and deploys production. Never self-certifies staging; nothing reaches main…
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…