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 persona-routergit 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/persona-router)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/persona-router"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/persona-router/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/persona-router"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/persona-router.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 | $0.00130 | $0.02510 |
| Opus 5.5 | $0.00052 | $0.01004 |
| Sonnet 5.5 | $0.00026 | $0.00502 |
| Haiku 4.5 | $0.00013 | $0.00251 |
Grade A, and why
persona-router 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona Router
从已安装的 N 个 persona skill 里,挑出最懂这个问题的 1-3 个。
Announce at start: "I'm using the persona-router skill to scan installed persona manifests and recommend the best matches for your question."
Overview
当你蒸馏了十几个 persona skill(同事、导师、公众人物、领域专家……),每次面对一个新问题,你都要在脑子里过一遍"这个问题谁最懂"。Router 把这步自动化:读所有 persona 的 manifest.json,按问题语义打分,给出排序推荐,你挑一个或几个触发。
Router 不回答问题,只负责把合适的 persona 推到你面前。
When Router Adds Value (Be Honest)
PRD 明确指出:
"router 和 debate 在 persona skill 数量 <10 之前没价值。" —
docs/.../prd.md§8 Q6
在下面这些情况,不要用 router:
| 场景 | 更好的做法 |
|---|---|
| 只装了 1-3 个 persona | 直接叫名字 |
| 问题明显属于某个 persona 的主场 | 直接触发那个 persona |
| 你想要的是"多方辩论"而非"挑人" | 直接用 persona-debate |
| persona 总数 <10 | 手动挑更快,router 开销反而亏 |
Router 的回报曲线在 persona 数 >= 10 后才变陡。
The Single Input Contract
Router 只读一种输入:符合 contracts/manifest.schema.json 的 manifest.json 文件。
这是 router 唯一认识的格式。任何 persona skill 如果没有合规的 manifest,router 会直接跳过(并在报告中列出)。Contract 路径(相对仓库根):
plugins/persona-distill/contracts/manifest.schema.json
Schema 里 router 实际用到的字段:
schema_type— 9 种 persona schema 之一identity.name/identity.display_name/identity.description/identity.domains/identity.subject_type— 匹配语义components_used— 19 个共享组件的激活集合(v0.3.0 起含 execution-profile)triggers— 触发短语(用来做二次验证)density_score/validation_score— 质量信号unvalidated— 未验证警告
不在 schema 里的字段 router 一律忽略。
Four-Step Workflow
┌─────────────────────────────────────────────────────────────┐
│ PERSONA ROUTER FLOW │
├─────────────────────────────────────────────────────────────┤
│ │
│ Step 1: 接收用户问题 │
│ ↓ │
│ Step 2: 扫描 installed persona skills │
│ └─ 读所有 manifest.json │
│ (符合 contracts/manifest.schema.json) │
│ ↓ │
│ Step 3: 在匹配维度上打分 │
│ ├─ schema_type relevance │
│ ├─ identity.domains keyword overlap │
│ ├─ components_used coverage │
│ └─ density_score / validation_score 调权 │
│ ↓ │
│ Step 4: 输出 1-3 条推荐(rationale 可见) │
│ └─ 按 templates/recommendation-template.md 格式 │
│ │
└─────────────────────────────────────────────────────────────┘
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.
- 1mo ago First seen · 208 lines · 130 tokens per session scan A f4c5a1cafb65
persona-router is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 130 tokens to every session and 2,510 once invoked, about $0.0005 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 2026-09-05.
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…