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 talesofai/okp --skill okp-searchgit clone --depth 1 https://github.com/talesofai/okpWrote 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/talesofai/okp/okp-search)<a href="https://agentmods.dev/skills/talesofai/okp/okp-search"><img src="https://agentmods.dev/badge/skills/talesofai/okp/okp-search/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/talesofai/okp/okp-search"><img src="https://agentmods.dev/badge/skills/talesofai/okp/okp-search.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 | $0.00047 | $0.01369 |
| Opus 5 | $0.00023 | $0.00685 |
| Sonnet 5 | $0.00009 | $0.00274 |
| Haiku 4.5 | $0.00005 | $0.00137 |
Grade A, and why
okp-search 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okp-search — 知识搜索 Skill
CRITICAL — 开始前 MUST 确认 okp CLI 已安装并可连接 API:
npm install -g @markbangwu/okp
okp domains # 确认 API 可达
何时使用
- agent 需要查找知识(角色、画风、操作手册、社媒分享等)。
- 回答用户问题时需要检索 Open Knowledge Protocol 中的结构化知识。
- 遍历概念之间的关系(通过 links)。
读权限
公开 domain 对所有已认证用户可读。private domain 只对显式受邀的 reader / writer 和创建者 host 可见;全局 admin 也没有读取旁路,必须先接受邀请。
写入权限见 okp-import;本 skill 只读。
检索循环(严格按此顺序)
Step 1: 确定 domain
okp domains # 列出所有领域
okp domains -q <keyword> # 按名称模糊找领域
返回字段:domain、concept_count、has_readme、visibility。
concept_count=0 表示已定义 README 但还没有 concept。
private domain 在未获邀请前不会出现在列表、搜索、sample、links 或 export 结果中。
Step 2: 读 domain README(必做)
每个 domain 的 README 定义了:数据是什么、有哪些 type、frontmatter 有哪些可过滤字段、怎么搜。
okp domain <domain>
禁止跳过 README 直接瞎搜。 不同 domain 的字段和用法不同,参数要以 README 为准。
Step 3: 不熟悉时先 sample
okp sample --domain <domain> --limit 5
看几条真实数据,确认 title / tags / frontmatter 长什么样,再决定怎么搜。
Step 4: 按 README 做精确搜索
根据 README 里的 schema 和 How to use,选择合适的组合:
# 列出某个 domain 的 concept(无 query 即按 domain 浏览;默认 limit 50)
okp search --domain <domain>
okp search --domain <domain> --limit 100
okp search --domain <domain> --limit 50 --offset 50
# 结构过滤(domain / type / tag 等)
okp search --domain <domain> --type <type>
okp search --domain <domain> --tag <tag>
# frontmatter 过滤(字段名以 README 为准)
okp search --domain <domain> --filter <field>=<value>
okp search --domain <domain> --filter <field>=<value> --sort date:desc
# 文本 / 语义查询
okp search "<query>" --domain <domain>
okp search "<query>" --domain <domain> --type <type>
原则:
- 要浏览某 domain 下有哪些 concept →
okp search --domain <domain>(可加--limit/--offset分页) - 知道具体实体名 → 文本查询
- 知道结构化字段(谁发的、哪个群、哪个 wiki)→
--filter,比纯文本更准 - 多字段可叠加,均为 AND
- 时序类数据用 README 推荐的
--sort - 精确字符/子串命中优先;语义结果作为补充(实现细节对用户透明,不必在回答里展开)
Step 5: Light list → 精读
搜索和 sample 返回摘要列表(id、title、description、tags、frontmatter)。
不要直接把列表当正文用。 选 1–3 个最相关的再 get:
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 · 148 lines · 47 tokens per session scan A adbc39733a54
okp-search is a skill published in the GitHub repository talesofai/okp (5 stars, last pushed 16d ago), licensed MIT. It adds 47 tokens to every session and 1,369 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
gap-to-topic
Turn a research area into a go/no-go decision dossier for ONE candidate thesis/proposal topic — a 3-gate verdict (is the gap open? is it a contribution? is it feasible?) with the evidence laid out so the researcher can verify it. Use when the user asks "is this gap worth pursuing", "help me pick a thesis topic", "is…
research-design-helper
Guide a researcher through 5 Socratic segments — research question sharpening, expected mechanism, identifiability check, validation plan, risk register — and produce .research/designbrief.md. Use when the user asks to "frame this research question", "design my study", "help me think through what model to build"…
paper-memory-builder
Convert a paper draft + figures + Zotero metadata into reusable .paper/claims.yml and .paper/figures.yml files so the academic-writing-skills skill can do writing, revision, and audit passes without re-reading the manuscript every time. Use when the user asks to "build paper memory", "extract claims from this…
research-context-compressor
Inspect a research repository and write a compact .research/ workspace manifest (projectmanifest.yml, experimentmatrix.yml, datadictionary.yml) so future AI sessions can orient themselves without rescanning the whole repo. Use when the user asks to "compress this project context", "create a research manifest", or…
migrate-v0-to-v1
Migrate a Scraps wiki from v0 to v1. Use this whenever the user asks to upgrade Scraps, migrate v0 wiki syntax/config, convert implicit tags to explicit #[[tag]], move from scraps-writer to scraps, or audit a wiki for v1 readiness. This skill is designed for one-pass LLM-led migrations that discover the latest v0 and…
research-workflow-orchestrator
Run a resumable end-to-end research workflow that automates low-risk work, pauses at explicit human decision gates, records provenance, and routes each stage to the appropriate research-hub skill or MCP tool.