Octos is a self-hosted AI assistant that runs on a user's computer and can connect to different AI providers, execute code, browse the web, remember information, schedule jobs, and create documents through browser, terminal, and messaging interfaces. The catalogue entries extend or configure this assistant's workflows.
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 octos-org/octos --skill deep-searchgit clone --depth 1 https://github.com/octos-org/octosWrote 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/octos-org/octos/deep-search)<a href="https://agentmods.dev/skills/octos-org/octos/deep-search"><img src="https://agentmods.dev/badge/skills/octos-org/octos/deep-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/octos-org/octos/deep-search"><img src="https://agentmods.dev/badge/skills/octos-org/octos/deep-search.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 | $0.00000 | $0.02338 |
| Opus 5.5 | $0.00000 | $0.00935 |
| Sonnet 5.5 | $0.00000 | $0.00468 |
| Haiku 4.5 | $0.00000 | $0.00234 |
Grade A, and why
deep-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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Search
Overview
The search tool does multi-round research: octos's key-less metasearch first, then a self-hosted SearXNG if configured, then any search API key you added, polite page reading (honest User-Agent, per-host spacing, a real browser only to render JS-heavy pages), reference chasing, and a cited report plus structured items. News, science and software searches work with no API key; key-less general search gets web results from results-page search (DuckDuckGo, then Bing; on unless the operator turned it off) alongside Wikipedia and Wikidata. This file is always in context, so it stays short; the tool's input schema lists every parameter.
Parameters
Use this native Rust tool for deep research; its search engines use sandboxed
OctoScript internally. Do not route ordinary research to run_pipeline, DOT,
or graph IR. The host supplies synthesis from the saved strong research
lane, or the chat provider when no strong lane is configured. Use deep_crawl
for bounded reading of a specific site's rendered pages, then consolidate
that evidence into the final report when needed.
- query (required); depth 1-3 (default 2; 10/30/50 pages); max_results per provider per round (default 8).
- output:
report(default, Markdown) oritems(structured JSON; the report is still written). - lang: BCP-47 code(s), e.g.
"en"or["en", "zh-CN", "es"]. Each language is searched separately and results are kept to those languages (unknown-language results are kept). - query_by_lang: the query in each language's own words, e.g.
{"zh": "人工智能 监管"}with query"AI regulation". Without it every language gets the same text, so an English query finds few Chinese pages; translate the query yourself when researching several languages. - region: ISO country, e.g.
US,TW(Google News edition, Brave/Serper country). - since: ISO date or
24h/7d/2w/3m/1y. Sent to providers that support it and applied to feed/page dates (undated results are kept). Use this instead of adding years or "latest" to the query. - category:
news,general,science,it,socialorauto(default: news whensince≤ 31 days or the query mentions news/latest/today, else general). - max_per_domain, domains_allow, domains_deny: source limits (Google News links count against the publisher).
- render:
auto(default) oroff(plain HTTP only). - search_engine: one provider to try first (
metasearch,gdelt,google_news_rss,searxng,serper,tavily,perplexity,brave,you) orall.
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.
- 1mo ago Changed · +7 lines c0c00f062920
- 1mo ago Changed d7130ea3e45c
- 1mo ago Changed · +1 lines 37f66549cd3f
- 1mo ago Changed · -20 lines 9cdf70cb8f84
- 2mo ago First seen · 72 lines · 0 tokens per session scan A 1a961c597e02
deep-search is a skill published in the GitHub repository octos-org/octos (766 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,338 tokens. 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.
deep-search compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deep-searchoctos-org/octos | Skill | 766 | yesterday | Apache-2.0 | A | 0 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |