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-agent-creatorgit 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-agent-creator)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-agent-creator"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-agent-creator/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-agent-creator"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-agent-creator.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 | $0.00114 | $0.01265 |
| Opus 5 | $0.00057 | $0.00633 |
| Sonnet 5 | $0.00023 | $0.00253 |
| Haiku 4.5 | $0.00011 | $0.00127 |
Grade A, and why
speclite-agent-creator 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.
What it actually says
[Overview（技能说明）]
Speclite Agent Creator 用于创建或迁移符合 SpecLite 运行模型的 Agent 定义包。它专门处理 speclite-agent-* / bmad-agent-* 这类以 persona 激活、[agent] 定制块、菜单分发和持续角色身份为核心的 role activation skill，不把它们误当作普通 [workflow] Skill。
[Core Capabilities（核心能力）]
- Agent 对象识别：识别以 persona、[agent]、menu dispatch 和 dismiss 前持续身份为核心的 Agent 定义包。
- Persona 语义保留：保留角色名、title、icon、role、identity、communication_style、principles、persistent_facts、激活步骤和持续身份规则。
- 运行模型转换：把 _bmad/scripts、_bmad/custom、_bmad/bmm/config.yaml 转换为 {speclite-runtime-root}/scripts、{speclite-runtime-root}/custom 和 merged runtime config。
- Agent 定制面生成：保留 customize.toml 的 [agent] 命名空间和结构合并规则，不转换成 [workflow]。
- 菜单映射与依赖规划：将 agent.menu 中的 skill = "bmad-*" 映射为已存在的 speclite-* 目标，无法确认时列入风险清单。
- Prompt 文件归类：把 Agent 根目录下的规约型 prompt Markdown 迁入 references/ 或 assets/，同步更新 {skill-root} 引用。
- 交接检查：生成后交给 speclite-agent-lint，覆盖 Agent block、菜单目标、路径残留、版本和文件归类。
[Workflow（执行流程）]
1. 确认输入：源 Agent 目录、目标 Agent 名称、目标阶段目录、是否需要英文入口；若缺失，一次最多询问 3 个问题。
2. 完整阅读 references/creation-workflow.md 与 references/agent-migration-baseline.md，建立源目标映射，不直接套用普通 workflow Skill 迁移规则。
3. 盘点源目录：读取 SKILL.md、customize.toml、根目录 prompt Markdown、菜单 skill 和 prompt 引用、运行时路径与配置字段。
4. 规划目标文件树：默认输出到 assets/source/speclite/sdlc-skills/<phase>/<speclite-agent-name>/，入口和配置留根目录，规约文档进 references/，模板骨架进 assets/。
5. 转换入口和配置：SKILL.md 使用 Speclite frontmatter，激活协议切换到 --key agent 的 Speclite resolver，customize.toml 保持 [agent]。
6. 转换菜单：把已存在的 bmad-* 目标映射为同名 speclite-* 目标；无法确认时不得猜测实现，必须在风险清单中标注。
7. 自检并交接：检查 BMad 残留、Agent 语义、菜单目标、引用文件、版本一致性和根目录 Markdown 白名单，输出建议运行的 speclite-agent-lint。
[Notes（注意事项）]
- 本 Skill 属于 support-skills/，只服务 SpecLite canonical skill 源定义创建和迁移，不属于目标项目默认 SDLC runtime 安装集合。
- 本 Skill 只迁移 Agent 定义向目录；普通 bmad-* workflow Skill 继续使用 speclite-skill-creator。
- customize.toml 必须承载 [agent] 默认定制面；不得按 workflow 规则改成 [workflow]。
- 当前运行规约不得依赖 _bmad、config.yaml、/bmad:* 或源码仓库路径作为 runtime 位置。
- config.toml.example 如生成，只能说明目标项目 runtime 配置结构，不能作为 fallback。
- Agent 包的 SKILL.en.md 是可选镜像；如存在，必须与中文 canonical 入口保持版本、路径和激活语义一致。
- 菜单项引用的本地 prompt 文件必须真实存在；迁移到 references/ 后必须同步更新 prompt 文本。
- 不得为了格式统一删除 persona、问候、菜单停顿、模糊匹配、持续角色身份等 Agent 核心语义。
[Generation Metadata（生成信息）]
本 Skill 由 speclite-agent-creator 维护并纳入 SpecLite support-skills 体系。如需修改，必须同步更新 SKILL.md、SKILL.en.md、CHANGELOG.md 与相关 references。
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.
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 · 44 lines · 114 tokens per session scan A 909320d6a5b6
speclite-agent-creator is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 114 tokens to every session and 1,265 once invoked, about $0.0006 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.
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…
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…
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…