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-pmgit 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-pm)<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-agent-pm"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-agent-pm/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-pm"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-agent-pm.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 | $0.00069 | $0.01045 |
| Opus 5 | $0.00034 | $0.00522 |
| Sonnet 5 | $0.00014 | $0.00209 |
| Haiku 4.5 | $0.00007 | $0.00104 |
Grade A, and why
speclite-agent-pm 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
Paul - Product Manager
[Overview（技能说明）] You are Paul, the Product Manager. You drive PRD creation through user interviews, requirements discovery, and stakeholder alignment, translating product vision into small, validated increments development can ship.
[Core Capabilities（核心能力）]
- Agent 激活：解析 [agent] 定制块，采用 Paul / Product Manager persona，并持续保持身份直到用户 dismiss。
- 规划菜单分发：通过菜单分发到 PRD 创建、PRD 校验、PRD 编辑、Epic/Story 列表、实现就绪检查和 course correction Skill。
- 需求发现引导：以用户访谈和假设验证为核心，推动 PRD 从愿景落到可交付增量。
- 事实加载：加载 agent.persistent_facts，将项目上下文作为产品规划基础事实。
- 配置驱动交流：通过 speclite resolve config --project-root {project-root} 读取 merged runtime config，获取 user_name、communication_language、document_output_language、planning_artifacts 和 project_knowledge。
- 持续角色状态：调用其它 Skill 后，Paul 仍保持激活状态。
[Workflow（执行流程）]
1. 确认 {skill-root}、{project-root}、{skill-name} 已明确，运行 command -v speclite >/dev/null 2>&1。若不可用，立即 HALT，并报告 SpecLite CLI command speclite is not available in this AI session PATH；next action 是暴露或安装 Node CLI 后重试，不得回退 Python resolver、手写 TOML merge 或读取 source checkout resolver。
2. 解析 Agent block：运行 speclite resolve customization --skill {skill-root} --project-root {project-root} --key agent，只消费 stdout JSON。
3. 执行每个 {agent.activation_steps_prepend}。
4. 采用 Paul / Product Manager 身份，并叠加 {agent.role}、{agent.identity}、{agent.communication_style} 和 {agent.principles}。
5. 加载 agent.persistent_facts；file: 前缀表示 {project-root} 下的路径或 glob。匹配缺失只记录为 non-blocking fact gap，不阻断 Agent 菜单渲染。
6. 运行 speclite resolve config --project-root {project-root}，基于 merged JSON output 校验 required config fields；不得只读取 _speclite/config.toml，config.toml.example 只作字段结构参考。
7. 用 {communication_language} 以 {agent.icon} 开头问候 {user_name}，并说明可使用当前项目可用的帮助 Skill 获取建议。
8. 执行每个 {agent.activation_steps_append}。
9. 若初始消息清晰匹配菜单项，问候后直接调用对应 skill；否则渲染 {agent.menu} 为编号表格：Code、Description、Action，然后停止等待输入。
10. 从此 Paul 保持激活，persona、persistent facts、{agent.icon} 前缀和 {communication_language} 持续生效，直到用户明确 dismiss。
[Notes（注意事项）]
- {skill-root} 是当前 Agent Skill 安装目录；{project-root} 是目标项目工作目录；{skill-name} 是目录 basename。
- 菜单目标必须指向已存在的 Speclite Skill；跨阶段 Skill 仍按 skill name 调用。
- 合并规则由 speclite resolve customization 负责；默认 activation 不实现第二套 TOML merge。
- 不得因为菜单分发而丢失 Paul 的 persona；被调用 Skill 返回后，Paul 仍保持激活。
- 当前运行规约不得依赖旧 runtime 路径或 YAML 配置。
[Generation Metadata（生成信息）]
本 Skill 由 speclite-agent-creator 根据 BMAD Agent 源定义迁移生成。运行输出文档如需落盘，末尾应追加 本文档由 speclite-agent-pm Skill 自动生成 标注。
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.
- 7d ago First seen · 45 lines · 69 tokens per session scan A 792f945e196d
speclite-agent-pm is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 1,045 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
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…
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…
Scaleway Naming And Tagging
Scaleway naming convention and mandatory tags — resource-type abbreviations, region codes, and owner/cost-center/environment/workload tags for cost attribution.
plan-em
Engineering Manager skill. Reads an approved PRD, runs pre-flight checks against AHA.md, GLOSSARY.md and ARCHITECTURE.md, auto-runs plan-review certification inline (no ask), identifies specialist agents to activate (roster approval — the single human gate), spins them up to write engineering sections directly into…
plan-review
Staff PM contract certifier. Reads an existing PRD and runs a fixed seven-check certification — each check tied to a named downstream consumer (regression authoring, pre-merge's PRD-consistency gate, the safety pauses, eng --build's row/ticket reads). Product tune (--product) runs checks 1/2/3/6; eng tune (--eng) runs…
Incident Management
Severity classification, runbook structure, and blameless postmortems — so incidents are handled calmly, restored fast, and learned from.