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 pieable/dragon-ball-agent --skill search-source-registrygit clone --depth 1 https://github.com/pieable/dragon-ball-agentWrote 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/pieable/dragon-ball-agent/search-source-registry)<a href="https://agentmods.dev/skills/pieable/dragon-ball-agent/search-source-registry"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/search-source-registry.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00860 |
| Opus 5 | $0.00015 | $0.00430 |
| Sonnet 5 | $0.00006 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
search-source-registry 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 6d 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
搜索来源注册表
这是一张搜索前参考的入口表，不是一套固定搜索词。研究者负责理解问题、选择来源和查询、判断结果是否充分并形成结论。程序只执行明确的收集、过滤、去重和覆盖记录。先判断什么来源最接近当前问题的原始记录，再从这些入口找候选。普通搜索用于发现未知入口和补缺口。
怎么用
- 明确要找什么、时间或版本范围，以及怎样才算覆盖。区分“尽量列全候选”和“核实一个已知事实”。
- 只读取与任务有关的来源表：
- 通用信源分级、搜索路线和停止条件：
references/general-web-research.md - 代码、依赖、版本、Bug、标准和安全问题：
references/code-research.md - 指定时间窗内的半导体新闻：
references/sources.json。需要枚举候选时运行下述程序。
- 通用信源分级、搜索路线和停止条件：
- 信源等级针对当前主张判断，不按网站固定分级。同一份公司公告可以直接证明“公司宣布了什么”，不能单独证明“产品实际最好”。
- 保存每个入口的实际状态。入口失败、需要登录、需要浏览器、没有相应适配器或没有检查，都要明确写出。“没有找到”不能代替“没有发生”。
- 多人核验时，每个候选只交给一个人。只有来源入口不同、已有结果异常为空或需要独立复核时，才允许受控重复。
已有程序
需要枚举可复用代码或依赖候选时，运行：
python scripts/discover_code_candidates.py --query "<功能描述>" --ecosystem <生态> --output <json路径>
生态可以是 github、python、npm、rust、go 或 nuget，同一次任务可以重复指定查询和生态。程序从代码托管平台和包注册表枚举候选，保留许可证、维护时间、发行、下载或使用信号以及每个入口的覆盖状态。source_queries_completed 只表示来源查询完成，不表示候选充分。程序不计算统一总分，也不决定采用哪个项目。GitHub token 只从 GITHUB_TOKEN 环境变量读取，未设置时使用公开接口的较低限额。
需要枚举指定时间窗内的半导体新闻候选时，运行：
python scripts/collect_candidates.py --since <ISO时间> --until <ISO时间> --output <json路径>
时间窗使用左闭右开区间。输出中的 candidates 是待核验材料，source_checks_completed 和 coverage 只表示哪些入口完成了机械检查。error 和 manual_required 都不算已检查，已检查也不表示新闻已经列全。
运行现有程序前不需要先读取源码。任务状态、游标和输出放在 Skill 目录外。
委派和直接搜索
- 主任务委派需要本 Skill 的联网搜索时，由实际执行搜索的 web-researcher 读取相关来源表，并交回候选、覆盖状态、核验结论、直接链接和会改变判断的缺口。主任务打开会改变最终结论、与其他来源矛盾或可能导致高代价行动的原始材料。
- 没有专门来源表时，按
references/general-web-research.md搜索。发现可复用的新入口时，先核验它对哪些主张有效、覆盖什么范围以及是否稳定，再考虑加入注册表。
注册表只说明应从哪里开始，不保证登记来源永远可访问，也不代表全球全部来源。
What ships with it
7 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.
- 6d ago First seen · 43 lines · 30 tokens per session scan A fa247b5879c3
search-source-registry is a skill published in the GitHub repository pieable/dragon-ball-agent (11 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 860 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…