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 rfdiosuao/AgentSkill --skill atypica-researchgit clone --depth 1 https://github.com/rfdiosuao/AgentSkillWrote 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/rfdiosuao/agentskill/atypica-research)<a href="https://agentmods.dev/skills/rfdiosuao/agentskill/atypica-research"><img src="https://agentmods.dev/badge/skills/rfdiosuao/agentskill/atypica-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/rfdiosuao/agentskill/atypica-research"><img src="https://agentmods.dev/badge/skills/rfdiosuao/agentskill/atypica-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 | $0.00085 | $0.02736 |
| Opus 5.5 | $0.00034 | $0.01094 |
| Sonnet 5.5 | $0.00017 | $0.00547 |
| Haiku 4.5 | $0.00009 | $0.00274 |
Grade A, and why
atypica-research scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
### Method 2: curl + jq (Best for scripting without MCP client) How it starts
The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
atypica Research
Access atypica.ai's multi-agent research framework for understanding consumer emotions, market perceptions, and decision preferences.
Calling Methods
Three ways to call the Research API, depending on your environment:
Method 1: MCP Client (Recommended for AI assistants)
If tools starting with atypica_ are already available, the MCP server is configured. Otherwise, configure it:
- Endpoint:
https://atypica.ai/mcp/study - API Key: From https://atypica.ai/account/api-keys (format:
atypica_xxx) - Authentication: HTTP header
Authorization: Bearer <api_key>
Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"atypica-research": {
"transport": "http",
"url": "https://atypica.ai/mcp/study",
"headers": {
"Authorization": "Bearer atypica_xxx"
}
}
}
}
Method 2: curl + jq (Best for scripting without MCP client)
When you don't have an MCP client, curl + jq is the most flexible combination. All MCP tools are plain JSON-RPC over HTTP:
export ATYPICA_TOKEN="atypica_xxx"
export ATYPICA_ENDPOINT="https://atypica.ai/mcp/study"
# Generic pattern: call any tool
call_tool() {
local tool_name="$1"
local args="$2"
curl -s -X POST "$ATYPICA_ENDPOINT" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $ATYPICA_TOKEN" \
-d "{\"jsonrpc\":\"2.0\",\"method\":\"tools/call\",\"params\":{\"name\":\"$tool_name\",\"arguments\":$args},\"id\":1}"
}
# Create research session
call_tool atypica_study_create '{"content":"Research young people coffee preferences"}' | jq '.result.structuredContent'
# Get messages (tail=5 for last 5 parts)
call_tool atypica_study_get_messages '{"userChatToken":"abc123","tail":5}' \
| jq '.result.structuredContent | {isRunning, messageCount: (.messages | length)}'
# Check for pending interactions
call_tool atypica_study_get_messages '{"userChatToken":"abc123","tail":3}' \
| jq '.result.structuredContent.messages[-1].parts[] | select(.state == "input-available") | {type, toolCallId}'
# Get report
call_tool atypica_study_get_report '{"token":"report_xxx"}' | jq '.result.structuredContent | {title, shareUrl}'
# Search panels
call_tool atypica_panel_search '{"query":"coffee"}' | jq '.result.structuredContent.data[] | {panelId, title, personaCount}'
What ships with it
3 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.
- 12d ago First seen · 305 lines · 85 tokens per session scan A 78e82226b5b5
atypica-research is a skill published in the GitHub repository rfdiosuao/AgentSkill (15 stars, last pushed 12d ago), licensed MIT. It adds 85 tokens to every session and 2,736 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
atypica-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| atypica-researchrfdiosuao/AgentSkill | Skill | 15 | 12d ago | MIT | A | 85 | Claude Code, Codex |
| comfyui-skill-openclawHuangYuChuh/ComfyUI_Skills_OpenClaw | Skill | 421 | 2mo ago | MIT | A | 125 | Claude Code, Codex |
| business-skill-factory26s5k7yty4-boop/business-skill-factory | Skill | 2 | 5mo ago | MIT | A | 119 | Claude Code, Codex |
| tmuxHKUDS/nanobot | Skill | 50k | yesterday | MIT | A | 20 | Claude Code, Codex |
| add-resendnanocoai/nanoclaw | Skill | 31k | yesterday | MIT | A | 16 | Claude Code |
| add-macos-statusbarnanocoai/nanoclaw | Skill | 31k | yesterday | MIT | A | 49 | Claude Code |
| sandbaseiflytek/skillhub | Skill | 5.4k | yesterday | Apache-2.0 | A | 67 | Claude Code |