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 gracefullight/docusaurus-plugins --skill oma-searchgit clone --depth 1 https://github.com/gracefullight/docusaurus-pluginsWrote 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/gracefullight/docusaurus-plugins/oma-search)<a href="https://agentmods.dev/skills/gracefullight/docusaurus-plugins/oma-search"><img src="https://agentmods.dev/badge/skills/gracefullight/docusaurus-plugins/oma-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/gracefullight/docusaurus-plugins/oma-search"><img src="https://agentmods.dev/badge/skills/gracefullight/docusaurus-plugins/oma-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 | $0.00059 | $0.01788 |
| Opus 5.5 | $0.00024 | $0.00715 |
| Sonnet 5.5 | $0.00012 | $0.00358 |
| Haiku 4.5 | $0.00006 | $0.00179 |
Grade A, and why
oma-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 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.
This is a copy
91% identical to oma-search — 187 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Agent - Intent-Based Search Router
Scheduling
Goal
Classify information-seeking requests, route them to the best search channel, attach trust labels, and return source-grounded results.
Intent signature
- User asks to search, find, look up, reference docs, inspect official documentation, search GitHub/GitLab code, or gather web research.
- Another skill needs reusable search infrastructure with trust scoring.
When to use
- Finding official library/framework documentation
- Web research for tutorials, examples, comparisons, and solutions
- Searching GitHub/GitLab code for implementation patterns
- Any query where the search channel is unclear (auto-routing)
- Other skills needing search infrastructure (shared invocation)
When NOT to use
- Local codebase exploration only -> use Serena MCP directly
- Git history or blame analysis -> use SCM Agent
- Full architecture research -> use Architecture Agent (may invoke this skill internally)
Expected inputs
- Query string, intent hint, or explicit flags such as
--docs,--code,--web,--strict,--wide,--gitlab - Optional required source type, recency, domain, or trust constraints
Expected outputs
- Ranked search results with route, source, trust label, and concise relevance summary
- Fallback explanation when primary route fails
- Source links or references suitable for the calling skill
Dependencies
- Context7 MCP for docs, runtime-native web search,
gh/glabfor code, Serena for local search resources/intent-rules.md,resources/trust-registry.md, execution protocol, examples, and checklist
Control-flow features
- Branches by classified intent, user flags, route success/failure, and trust constraints
- May call web/docs/code/local tools
- Scores domains at domain level only
Structural Flow
Entry
- Parse the query and flags.
- Classify the search intent.
- Select one best route unless ambiguity or flags justify more.
Scenes
- PREPARE: Parse query and classify route.
- ACT: Dispatch to docs, web, code, or local search.
- ACQUIRE: Collect search results and source metadata.
- VERIFY: Apply trust scoring and route-specific quality checks.
- FINALIZE: Present ranked results or fallback status.
What ships with it
6 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 · 178 lines · 59 tokens per session scan A 7c74416e7071
oma-search is a skill published in the GitHub repository gracefullight/docusaurus-plugins (23 stars, last pushed 27d ago), licensed MIT. It adds 59 tokens to every session and 1,788 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to oma-search, differing in 187 lines, and is treated as a copy.
Other skills, from other repositories
claude-code-dmwork
Connect to DMWork messaging platform as an AI bot via the OpenClaw DMWork adapter plugin.
vs-chat
Conversational search runtime: send messages, keep sessions consistent, and verify retrieval behavior and responses.
cometchat-android-v6-core
Foundational rules for the CometChat Android UI Kit v6 — the two UI cohorts and their artifacts, credentials via the gitignored assets settings file, initFromSettings → login → render ordering, the component map, and the production-ready core chat surface. Read this first for any Android CometChat task. Triggers…
cometchat-react-v7-core
Add CometChat chat to a React app end-to-end — detect the project, get & verify dashboard credentials, init→login→render with CometChatProvider, and the drop-in conversation UI. The core knowledge every other React v7 skill builds on. Triggers: 'add chat to my react app', 'integrate cometchat react', 'set up cometchat…
cometchat-android-v6-compose-placement
Where the CometChat Android v6 chat UI goes in a Jetpack Compose app — the default conversations→message NavHost flow, growing to the tab-based app (chats/users/groups/calls + detail, thread and search routes + incoming calls), a single one-to-one screen, or chat embedded in an existing composable, with a correct back…
cometchat-android-v5-sdk
Build chat on Android with the headless CometChat Chat SDK v5 and your OWN UI — init/login ordering, the method map, request-builder pagination, listener lifecycle, and a production-ready app surface (optimistic updates, error states, sized shell). Use when the app needs custom UI instead of the drop-in UI Kit.…