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 Rylaispirit/rylai-codex-hermes-skills --skill deep-researchgit clone --depth 1 https://github.com/Rylaispirit/rylai-codex-hermes-skillsWrote 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/rylaispirit/rylai-codex-hermes-skills/deep-research)<a href="https://agentmods.dev/skills/rylaispirit/rylai-codex-hermes-skills/deep-research"><img src="https://agentmods.dev/badge/skills/rylaispirit/rylai-codex-hermes-skills/deep-research/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/rylaispirit/rylai-codex-hermes-skills/deep-research"><img src="https://agentmods.dev/badge/skills/rylaispirit/rylai-codex-hermes-skills/deep-research.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 | $0.00024 | $0.00455 |
| Opus 5 | $0.00012 | $0.00228 |
| Sonnet 5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
deep-research 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 10d 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
Rylai Codex-Hermes-Claude Edition | Original portable workflow by Rylai
Runtime Compatibility
- Codex: install under
~/.agents/skills/deep-research. - Hermes: install under
~/.hermes/skills/deep-researchor expose the bundle throughskills.external_dirs. - Claude Code: install under
~/.claude/skills/deep-researchor<project>/.claude/skills/deep-research. - Claude.ai and Cowork: upload and enable the matching per-skill ZIP.
- Resolve bundled files relative to this skill directory; do not depend on paths from another machine.
- Check tools, packages, credentials, network access, and runtime capabilities before execution.
Portable Deep Research
Produce a source-backed answer to a question that genuinely needs multi-source research.
Workflow
- Define the research question, scope, date boundary, audience, and decision the report should support.
- Break the question into independent sub-questions and identify preferred primary sources.
- Search broadly, then open and inspect the most relevant sources.
- Use parallel research agents only when the runtime exposes delegation and the subtasks are independent.
- Build an evidence table containing claim, source, date, confidence, and contradiction notes.
- Triangulate important claims and explain disagreements instead of silently selecting one source.
- Synthesize the answer with citations attached to the claims they support.
- State unresolved gaps, stale evidence, and inference separately from verified fact.
Boundaries
- Ask a clarification question only when ambiguity materially changes the research result.
- Never invent a citation, quote, URL, statistic, publication date, or source conclusion.
- For current topics, verify freshness at execution time.
What ships with it
1 file 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.
- 10d ago First seen · 47 lines · 24 tokens per session scan A 4fbc73537182
deep-research is a skill published in the GitHub repository Rylaispirit/rylai-codex-hermes-skills (55 stars, last pushed 27d ago), licensed MIT. It adds 24 tokens to every session and 455 once invoked, about $0.0001 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
deep-research
Autonomous multi-step deep research engine implementing an iterative Think → Search → Extract → Synthesize → Stop loop. The LLM drives every decision: what to search, what's relevant, what's missing, and when to stop. Produces a cited, magazine-quality report with inline citations, category- specific formatting, and…
image-studio
Generate, edit and upscale AI images via fal.ai through a three-stage studio workflow — brainstorm a strong prompt with the user, prototype cheaply and iterate on feedback, then produce a finalised image. Use when the user wants image generation or editing through the local fal.ai helper workflow, including requests…
website-scraping
Generic playbook for extracting structured data from any website — hotel prices, flight fares, e-commerce listings, real estate, jobs, competitor product catalogues, anything where the goal is to turn one or more URLs into clean records on disk. Use this skill whenever the user mentions scraping, harvesting…
skill-maintainer
Track upstream drift and sync adapted skill libraries.
clips-studio
Use when the user wants to "make a video/clip", "generate a video from text", "animate this image/photo", "create a marketing reel / social video / teaser", "do a 3D / parallax move", "pan/zoom/orbit a shot", or mentions fal.ai, Kling, Veo or Seedance for video. Staged fal.ai workflow — brainstorm, draft cheaply…
library-rag
Semantic search over a personal library using Nemotron-3-Embed-1B embeddings + sqlite-vec. Index books, documents, any text corpus; query by meaning. Includes EPUB→Markdown conversion and MCP server for auto-available search tools.