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 85danf/agent-skills --skill windsurf-deep-researchgit clone --depth 1 https://github.com/85danf/agent-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/85danf/agent-skills/windsurf-deep-research)<a href="https://agentmods.dev/skills/85danf/agent-skills/windsurf-deep-research"><img src="https://agentmods.dev/badge/skills/85danf/agent-skills/windsurf-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/85danf/agent-skills/windsurf-deep-research"><img src="https://agentmods.dev/badge/skills/85danf/agent-skills/windsurf-deep-research.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 | $0.00040 | $0.01696 |
| Opus 5 | $0.00020 | $0.00848 |
| Sonnet 5 | $0.00008 | $0.00339 |
| Haiku 4.5 | $0.00004 | $0.00170 |
Grade A, and why
windsurf-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 8d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Structured teaching flow: gist, informed questions, research, progressive explanation.
Overview
Teach any topic through progressive disclosure. Deliver value immediately with a preliminary gist, then deepen research based on user needs.
Two modes: Single topic (default) or Comparison (when 2+ items detected).
Three depth tiers:
| Tier | Phases | Research Tracks | Deliverable |
|---|---|---|---|
| Quick | 0-1-2 | 0 | Conversational gist |
| Standard | 0-1-2-3-4-5+QA | 4 | Gist + study guide |
| Deep | All phases + QA | 5-6 + review | Gist + comprehensive doc |
Skill Directory
Supporting files are in the same directory as this SKILL.md. They are not auto-loaded — read them explicitly and only when needed (progressive disclosure) to avoid context bloat. Use absolute paths with Cascade's read_file tool.
agents/— Research guides for each research track.reference/— Search strategies, teaching tone, analysis tools (read only when needed).templates/— Output document templates (read when composing final output).
Phase 0: Topic Input
Parse topic from the user’s request. If invoked via @deep-research, treat the remaining text as the topic.
- No topic provided: ask for one.
- Comparison detected ("vs", "versus", "compared to", "or" between named items, 2+ items listed): confirm comparison mode.
Phase 1: Preliminary Assessment & Gist
Runs BEFORE asking any clarification questions.
- Run 1-2 web searches for a current overview of the topic using Cascade's search_web tool. Read the top results with read_url_content to ground the gist.
- Deliver gist conversationally to the user:
- What it is — 2-3 sentences
- Why it matters — the problem it solves
- Where it fits — ecosystem context
- Mental model — one-liner analogy ("Think of it as...")
- Internally note key dimensions for Phase 2:
- Main subtopics/areas
- Recent developments or controversies
- Common use cases
- Related/competing technologies
What ships with it
12 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.
- agents/community-searcher.md 1.8 KB
- agents/comparison-searcher.md 1.9 KB
- agents/deep-analyst.md 2.9 KB
- agents/docs-searcher.md 1.6 KB
- agents/integration-searcher.md 1.8 KB
- agents/synthesis-reviewer.md 1.4 KB
- agents/tutorial-searcher.md 1.7 KB
- reference/analysis-tools.md 3.4 KB
- reference/search-strategies.md 3.2 KB
- reference/teaching-tone.md 1.4 KB
- templates/comparison-guide.md 876 B
- templates/study-guide.md 1.2 KB
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.
- 8d ago First seen · 179 lines · 40 tokens per session scan A 26eac2128060
windsurf-deep-research is a skill published in the GitHub repository 85danf/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,696 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.