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 Battam1111/omniseek --skill omniseek-investigategit clone --depth 1 https://github.com/Battam1111/omniseekWrote 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/battam1111/omniseek/omniseek-investigate)<a href="https://agentmods.dev/skills/battam1111/omniseek/omniseek-investigate"><img src="https://agentmods.dev/badge/skills/battam1111/omniseek/omniseek-investigate/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/battam1111/omniseek/omniseek-investigate"><img src="https://agentmods.dev/badge/skills/battam1111/omniseek/omniseek-investigate.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 | $0.00046 | $0.01439 |
| Opus 5 | $0.00023 | $0.00720 |
| Sonnet 5 | $0.00009 | $0.00288 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
omniseek-investigate 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 13d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/omniseek-investigate
Deep investigation METHODOLOGY for OmniSeek. Teaches judgment patterns for composing retrieval primitives into multi-step evidence gathering. Tool facts (signals, handles, _meta, evidence graph schema, walled source mechanics) are in the server instructions, not here. This skill teaches HOW to use those facts well.
1. The 3-turn rhythm (sweep, zoom, structure)
Every deep investigation follows the same beat:
WAVE 1 (sweep): fire several independent tools in parallel via omniseek_gather.
A broad omniseek_search plus any tools whose results you need to make your
first judgment call (e.g. omniseek_resolve_identity for a person question,
omniseek_field_skeleton for a field question). One round-trip, all results at once.
Judge: read Phase A signals, handles, and _meta (per server instructions sections 3-5). Decide what to zoom on: which walled sources from excluded_relevant to chase, which identities to map, which papers to enrich, which talks to transcribe.
WAVE 2 (zoom): fire follow-ups via omniseek_gather, informed by WAVE 1 signals.
Structure: build an evidence graph from your findings (per server instructions section 6).
2. Investigation starting points
These are STARTING POINTS. Adapt, skip, extend based on what you find.
Person due-diligence
WAVE 1: omniseek_search + omniseek_resolve_identity.
WAVE 2: omniseek_coauthors + omniseek_paper_enrich + walled chase + omniseek_transcribe.
Key judgment: coauthor network reveals structural position; walled sources reveal candid views.
Lab / research group evaluation
WAVE 1: omniseek_search + omniseek_institution_cohort.
WAVE 2: omniseek_field_skeleton + omniseek_coauthors(top PI) + omniseek_paper_enrich + walled chase.
Key judgment: cohort shows who publishes there; citation neighborhood shows where they sit.
Field / topic mapping
WAVE 1: omniseek_search + omniseek_field_skeleton.
WAVE 2: omniseek_paper_recommend + omniseek_paper_enrich + omniseek_transcribe.
Key judgment: identify consensus core (high in_degree), frontier (recent, citing core), controversy.
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.
- 13d ago First seen · 106 lines · 46 tokens per session scan A 9815a8343fb0
omniseek-investigate is a skill published in the GitHub repository Battam1111/omniseek (49 stars, last pushed 2d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,439 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 2026-08-30.
Other skills, from other repositories
weekly-review
How this household runs its Sunday weekly review.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
mem0-remember
Stores a memory verbatim from user input with appropriate type classification and metadata. Use when the user says remember this, save this, store this, note that, or explicitly asks to record a decision, preference, convention, or learning.
status
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.