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 devcxl/mattpocock-skills-zh --skill wayfindergit clone --depth 1 https://github.com/devcxl/mattpocock-skills-zhWrote 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/devcxl/mattpocock-skills-zh/wayfinder)<a href="https://agentmods.dev/skills/devcxl/mattpocock-skills-zh/wayfinder"><img src="https://agentmods.dev/badge/skills/devcxl/mattpocock-skills-zh/wayfinder/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/devcxl/mattpocock-skills-zh/wayfinder"><img src="https://agentmods.dev/badge/skills/devcxl/mattpocock-skills-zh/wayfinder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.03182 |
| Opus 5 | $0.00028 | $0.01591 |
| Sonnet 5 | $0.00011 | $0.00636 |
| Haiku 4.5 | $0.00006 | $0.00318 |
Grade A, and why
wayfinder 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 11d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
一个模糊的想法来了——大到一个 agent 会话装不下,而且笼罩在迷雾之中:从当前位置到目的地的路线还不 visible。Wayfinding 就是寻找那条路线,而不是冲向目的地。本技能将其绘制为 Issue 跟踪器上的共享地图,然后逐个处理其决策 ticket——问题本身,其答案是一个决策,而非构建中的可交付物切片——直到路线清晰。
每个项目的目标各不相同,命名目标是绘图的第一个行为——它塑造了每一个 ticket。它可能是一份要交付并迭代的规格说明、一个在规划开始前要锁定的决策、或者一个原地进行的变更(如数据结构迁移)。地图是领域无关的——工程工作、课程内容,无论什么形态都适用。
规划,而非动手
Wayfinder 默认是规划工具:每个 ticket 解决一个决策,地图在路线清晰时完成——不再有任何需要决定的事情,就可以交给别人去动手了。想要直接动手做的冲动,通常是你已经抵达地图边缘的信号,是时候交接了。项目可以在其笔记中覆盖这一设定——将执行任务也纳入地图——但默认情况下,产出的是决策,而非可交付物。
用名称来引用
每个地图和 ticket 都是一个 issue,因此它有一个名称——它的标题。在人读取的一切内容中——叙述、地图的"已有决策"部分——都通过名称来引用,绝不使用原始 ID、编号或短横线标识。一堵 #42, #43, #44 组成的墙难以阅读;名称则一目了然。ID 和 URL 不会消失——但名称包裹着链接——它们只是活在名称内部,而不是替代它。
地图
地图是此仓库 Issue 跟踪器上的一个 issue,带有 wayfinder:map 标签——这是权威产出物。它的 ticket 是地图的子 issue。
地图是一个索引,而不是仓库。它列出已做出的决策并指向包含其细节的 ticket;一个决策只存在于一个地方——它的 ticket 中——因此地图从不重述它,只摘要它并链接。
地图、其子 ticket、阻塞关系和前沿查询在物理上位于何处,取决于具体的跟踪器。 Issue 跟踪器应已提供给你——如果没有,请告诉用户运行 /setup-matt-pocock-skills。查阅跟踪器文档的"Wayfinding 操作"一节了解此仓库如何表达它们。如果未提供跟踪器,默认使用本地 Markdown 跟踪器。
地图正文
整个地图以低分辨率加载,每个会话一次。打开的 ticket 不在此列出——它们是打开的子 issue,通过查询找到。
## 目的地
<到达此地图终点时的样子——该目标最终产出的规格、决策或变更。一两行;每个会话在选择 ticket 前都会以此为导向。>
## 笔记
<领域;每个会话应查阅的技能;此工作的固定偏好>
## 已有决策
<!-- 索引——每个已关闭 ticket 一行:足以判断相关性,然后点击链接获取 ticket 中的详细内容 -->
- [<已关闭 ticket 标题>](link) — <一行答案摘要>
## 尚未明确
<!-- 见"战争迷雾":范围内的迷雾,尚不能创建 ticket;随着前沿推进而毕业-->
## 范围外
<!-- 见"范围外":目的地之外排除的工作;已关闭,永不毕业-->
Ticket
每个 ticket 都是地图的子 issue;跟踪器的 issue ID 是其标识。其正文是问题,大小限制在一次 100K token 的 agent 会话:
## 问题
<该 ticket 解决的决策或调查>
每个 ticket 带有 wayfinder:<type> 标签——research、prototype、grilling、task 之一(见 Ticket 类型)。
一个会话通过将 ticket 分配给推动地图的开发人员来认领它,先做这个,在开始任何工作之前,这样并发会话会跳过它。那个分配人就是认领:一个打开的、未分配的 ticket 就是未被认领的。
阻塞关系使用跟踪器的原生依赖关系——这很关键,因为它能让前沿在视觉上呈现在跟踪器自己的 UI 中,让人可以在不打开地图的情况下看到哪些是可领取的。只有当一个跟踪器缺少原生阻塞功能时才回退到正文约定。一个 ticket 在所有阻塞它的 ticket 都关闭时即为已解除阻塞;前沿就是打开的、未阻塞的、未分配的子 ticket——已知领域的边界。
答案不是正文的一部分——它是在解决时记录的(见推进地图)。在解决 ticket 过程中创建的资产通过链接关联到 issue,而不是粘贴进去。
What ships with it
1 file 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.
- 11d ago First seen · 129 lines · 57 tokens per session scan A 21b5b7e3fc19
wayfinder is a skill published in the GitHub repository devcxl/mattpocock-skills-zh (340 stars, last pushed 6d ago), licensed MIT. It adds 57 tokens to every session and 3,182 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 2026-08-30.
Other skills, from other repositories
openspec-bulk-archive-change
Archive multiple completed changes at once. Use when archiving several parallel changes.
requirement-delivery
A workflow for turning a new software request into a small, working deliverable. It clarifies acceptance criteria, identifies boundaries, breaks work into demonstrable parts, and looks for existing code or tools to reuse.
loop-orchestrator
Operate a fleet of durable agent loops under .loop/ — schedule which loop runs next, assign agents to roles (maker vs checker), enforce promotion gates from propose-only to write access, allocate budgets, detect stalled or dead loops, and roll up fleet status into one report. Use when asked to "run the loops"…
creator-productivity
Task management and workspace memory for creative work sessions. Manages a TASKS.md file for project tracking, a two-tier memory system (CREATOR.md + creator-memory/), and a daily sprint structure. Use when organizing creative projects, tracking content tasks, or starting a focused work session.
product-management-expert
Product management expertise for strategy, discovery, prioritization, roadmaps, PRDs, metrics, and stakeholder communication. Use when defining what to build, why, and how to measure success.
todo-discipline
Use when starting any complex task (3+ steps) or before declaring work complete. Enforces todo/task state to match reality — merge updates + read verification. Prevents false completion.