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 xg-gh-25/SwarmAI --skill s_deep-researchgit clone --depth 1 https://github.com/xg-gh-25/SwarmAIWrote 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/xg-gh-25/swarmai/s_deep-research)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_deep-research"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_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/xg-gh-25/swarmai/s_deep-research"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_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 | $0.00050 | $0.02952 |
| Opus 5 | $0.00025 | $0.01476 |
| Sonnet 5 | $0.00010 | $0.00590 |
| Haiku 4.5 | $0.00005 | $0.00295 |
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 11d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Conduct systematic, multi-source research that produces well-cited, comprehensive analysis. Never generate content based solely on general knowledge -- the quality of output depends directly on the quality and quantity of research conducted beforehand.
Output Location
Save research documents to:
~/.swarm-ai/SwarmWS/Knowledge/Notes/YYYY-MM-DD-<topic>.md
Once finalized, move to Knowledge/Library/ for long-term reference.
Workflow: 5-Phase Research
Phase 0: Intent Classification & Strategy Planning
Goal: Before any search, classify the research intent and plan the optimal strategy. Output a structured plan that drives all subsequent phases.
Step 1: Classify the research intent. Pick the PRIMARY intent:
| Intent | Signal Words | Example |
|---|---|---|
factual |
"what is", "how does", "explain" | "How does Raft consensus work?" |
competitive |
"vs", "compare", "alternative", "竞品" | "SwarmAI vs OpenClaw" |
landscape |
"overview", "landscape", "what's out there", "调研" | "AI agent frameworks 2026" |
how_to |
"how to", "implement", "build", "tutorial" | "How to implement RAG with Bedrock" |
breaking_news |
"latest", "just happened", "今天", "刚刚" | "What did Anthropic announce today?" |
trend |
"trend", "direction", "future", "趋势" | "Where is agent memory heading?" |
person_org |
person name, company name, "@handle" | "Research Peter Steinberger" |
deep_technical |
"architecture", "internals", "source code" | "Claude Code SDK internal architecture" |
Step 2: Determine search parameters. Based on intent, set these BEFORE Phase 1:
| Parameter | factual |
competitive |
landscape |
how_to |
breaking_news |
trend |
person_org |
deep_technical |
|---|---|---|---|---|---|---|---|---|
| search_depth | basic | advanced | advanced | basic | basic | advanced | advanced | advanced |
| time_range | none | month | none | year | day/week | year | month | none |
| topic | general | general | general | general | news | news | general | general |
| source_priority | docs→papers→blogs | product pages→HN→blogs | industry reports→news→blogs | GitHub→SO→tutorials | news→social→blogs | reports→expert blogs→news | social→GitHub→blogs→news | source code→docs→talks |
| min_sources | 3 | 5 (both sides) | 5 | 3 | 3 | 5 | 4 | 3 |
| search_rounds | 2-3 | 3-5 | 3-5 | 2-3 | 2-3 | 3-5 | 3-4 | 2-4 |
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.
- 11d ago First seen · 270 lines · 50 tokens per session scan A d0404d9e6fa0
deep-research is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 2,952 once invoked, about $0.0003 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
workspace-analyzer
Inspect a workspace, identify temporary files, and perform only approved cleanup or organization steps.
project-notetaker
Formats unstructured meeting notes into a structured project report. Use this when the user provides raw notes or requests a summary of a meeting.
tura
Work in the Tura agent-runtime repository. Use for Tura architecture, Rust backend, GUI/TUI, prompts, commands, providers, sessions, documentation, tests, packaging, and release work in this directory.
remember
Routes user requests containing "remember", "recall", "checkpoint", "session", "todo", or "where were we" to the correct OpenEmpiric (OEM) MCP tool. Use when the user wants to persist, retrieve, or contextualize knowledge from project memory.
compile
Compile a deterministic CIGAR context bundle for the current task with an explicit token budget and inspectable manifest.
effect
Prepare, inspect, commit, and reconcile governed CIGAR effects while preserving explicit authorization and idempotency.