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 XRenSiu/claude-code-forge --skill pslgit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/xrensiu/claude-code-forge/psl)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/psl"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/psl/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/xrensiu/claude-code-forge/psl"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/psl.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 | $0.00249 | $0.04747 |
| Opus 5.5 | $0.00100 | $0.01899 |
| Sonnet 5.5 | $0.00050 | $0.00949 |
| Haiku 4.5 | $0.00025 | $0.00475 |
Grade A, and why
psl 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.
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
psl
输入一句到一段的产品需求（可附物料：旧 PRD、代码、设计稿、访谈、笔记），输出一份完整的
PSL-<产品/功能名>.md。本 skill 不规定步骤顺序——引擎自己排工作；下面给的是缺口、
世界的形状、判据与门。 写第一份 PSL 前先读 references/EXAMPLE.md（先见过一份"对的
样子"再动手，这是认识论顺序，不是流水线）。
缺口（这个 skill 补什么、不补什么）
引擎本就会推理、会写结构化文档、会编排问答——这些全部留给引擎。缺的恰好是：
- Σ（形状 + 来路纪律）：PSL 的六层模子长什么样；某个具体产品的私有世界内容从哪来；
- φ（判据）：什么算"世界写对了"——Domain Model 推翻测试、行为可判验收、消歧判据；
- γ（纪律）：提问何时问 / 何时不问 / 何时停；未知内容何时 seam；交付契约不可跳。
deletion 测试：撤掉本 skill，让引擎实现"按时间搜索记忆"，它会交出 {created_at} 加日历
筛选器——技术正确、产品错误。缺口真实存在。
入口判据：双轨裁决（先跑，决定该不该干）
对需求先问一件事：语义份额与确定性份额谁主导？
- (Σ+φ 占比 × 变化率) 高、Capability 难度低 → 写 PSL。 即：需求的难点在"世界怎么运转、 什么算对"（且这些语义随人/场景漂移），而不在实现原语本身。速判：把需求交给一个不了解 这个产品的工程师照字面做，他会不会做出技术正确、产品错误的东西？会 → PSL。
- 确定性主导 → 明说"这里 PRD 的精确恰好够用，套世界模型是过填"，然后停。 不虚构世界。 （支付校验、合规字段、固定列的报表导出，都属此类。）
- 混合需求 → 只对体验性内核写 PSL，确定性部分注明"留在 PRD，按字面做即可"。
- 用户给的是现成 PRD → 用同一判据裁决"该不该改写为 PSL"，两个方向的结论都合法。
诚实公理（世界内容只有三种来路，没有第四种）
运行本 skill 的引擎脑子里没有这个具体产品的世界。所以每一条世界内容必须有来路：
| 来路 | 什么内容 | 处理 |
|---|---|---|
| surface | 引擎已知但不会主动说的通用世界知识（领域常识、用户心理规律） | 自己填，不问；展示给用户确认 |
| elicit | 只有用户知道的私有内容（核心赌注、目标人群、关键承诺），且承重 | 问用户 / 从物料里抽 |
| seam | 私有但不承重；或问了答不上来（"不知道 / 直接写"） | 显式列入 Open Questions，写清为什么需要人来定 |
承重槽的定义：其取值会改变产品形状、或会翻转某条验收结果的槽。典型：核心 Vision 赌注、目标 Persona、关键 Mental Model 承诺、能推翻朴素数据结构的 Domain 实体。
第四种来路（编造、默认值糊上）不存在。用户没说、物料里没有、又不是通用常识的东西，一律 seam。
来路要写得能被核对。 [elicit:物料 <文件> §N] 里的文件名与章节号是给别人复核用的，凭记忆
写等于没写——本次审计就把 ARCHITECTURE §7 的内容记成了 lifecycle.md §7，而 lifecycle.md 根本
没有 §7。verify_psl.py --material-root <物料目录> 对文件与章节做存在性 flag（只 flag：物料可能
不在本机）。标来路时打开那份文件确认一次，比事后被 G1 抓到便宜。
世界（Σ）：一份 PSL 长什么样
骨架六层，上一层是下一层的定律（这是推导依赖，不是填表顺序）：
| 层 | 位点 | 写什么 |
|---|---|---|
| Vision | Σ | 产品为什么存在。一句能推翻朴素实现的根命题。 |
| Mental Model | Σ | 用户与 AI 共享的世界关键事实（如"时间不是时间戳"）。 |
| Domain Model | Σ | 核心实体 + 关联。必须能推翻朴素数据结构（否则这份 PSL 没干活）。 |
| State Machine | Σ | 实体状态流转（领域动力学，不是执行顺序）。 |
| Workflow | Σ+φ | 拆成 Σ（发生了什么）+ φ（消歧判据 + "对"的样子）。严禁写成 Step 1/2/3。 |
| Acceptance | φ-出口 | 怎样算"世界转对了"。每条都是"问 X → 返回 Y"的行为可判语句。 |
What ships with it
9 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.
- eval/fixtures/material-notes.md 186 B
- eval/fixtures/PSL-bad-elicit.md 2.4 KB
- eval/fixtures/PSL-continuation-ref.md 671 B
- eval/fixtures/PSL-dup-rule-id.md 2.4 KB
- eval/fixtures/PSL-no-rule-ids.md 2.4 KB
- eval/gate.json 6.4 KB
- eval/report.md 5.9 KB
- references/EXAMPLE.md 13 KB
- scripts/verify_psl.py 20 KB runs code
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 Changed d464694df2b5
- 1mo ago Changed · +22 lines 4f78d44f420b
- 1mo ago Changed · +34 lines df87e5258118
- 2mo ago First seen · 162 lines · 249 tokens per session scan A 82e97fac99f6
psl is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 249 tokens to every session and 4,747 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…