joehahn/portfolio-wave-rider
An AI agent reads an unstructured news feed and curates a watchlist, while a mechanical mean-variance optimizer handles the sizing that must be auditable. Research project by JMH DataSciences.
field: AI / ML
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit joehahn/portfolio-wave-rider/.claude ./rig-portfolio-wave-rider # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ curl -fsSL --create-dirs -o .claude/agents/report-writer.md https://raw.githubusercontent.com/joehahn/portfolio-wave-rider/main/.claude/agents/report-writer.md $ curl -fsSL --create-dirs -o .claude/agents/watchlist-curator.md https://raw.githubusercontent.com/joehahn/portfolio-wave-rider/main/.claude/agents/watchlist-curator.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Subagents (2)
| report-writer model: sonnet | Canonical format spec for the /review-portfolio and /initialize-portfolio reports. The orchestrating skills author the report inline in the main loop following the structure below; this subagent is re |
| watchlist-curator model: sonnet | Reads recent business news, the investor's wave thesis, and the current watchlist; proposes which tickers to add and which to remove. Returns a JSON payload to the orchestrating skill or backtest harn |
Permissions
deny (0)
—
ask (0)
—
allow (6)
Bash(.venv/bin/python -m src.cli:*)
Bash(.venv/bin/pytest:*)
Bash(mkdir -p data/*)
Bash(rm -f data/state/*.pkl)
Read(//**)
Edit(data/**)
Similar rigs
liangdabiao/claude-data-analysis
Create a data analysis AI agent with Claude Code. Make data analysis as simple as having a chat! 别忘了!claude code也是agent框架,类似langgraph,crewAI,autogen等等agent框架。我改造claude code搞一个数据分析智能体AI。 让数据分析变得像聊天一样简单!
Orchestrator 1.2k tok · · Q15
Mikacr1138/claude-bug-bounty
Enable efficient bug bounty hunting across Web2 and Web3 with a tool that supports full recon to detailed reporting.
Orchestrator 1.7k tok · · Q0
junjiezhou1122/ideascientist-claude-code
A native Claude Code translation of IdeaScientist for automatic, evidence-grounded research ideation.
Orchestrator 528 tok · · Q0
Gidntsquia/claude-config
My Claude Code agents, skills and settings
YOLO Cowboy 4.2k tok · · Q0