AI argues. Code settles. The losses stay on the page. A real HK + US brokerage account run by agents that must debate every call, settled by code the model never touches. Install the same decision workflow into your own agent: OpenClaw, Claude Code, Codex, or DeepSeek Harness.
- GitHub stars
- 10
- License
- MIT
- Added
- 2026-08-30
GitHub info
- GitHub stars
- 10
- License
- MIT
- Primary language
- Python
- Last push
- Aug 21, 2026, 6:20 AM
- Maintainer
- KCNyu
- Added
- 2026-08-30
Preview from README
Screenshots and GIFs extracted from the repository README (badges and avatars filtered out).
clawock dashboard cycling through its tabs
https://raw.githubusercontent.com/KCNyu/clawock/refs/heads/master/site/assets/dashboard.gif
Claude Code running the investment-decision workflow end to end: clawock init, clawock run prepare, Claude writing decision.json, clawock run publish returning status: published
https://raw.githubusercontent.com/KCNyu/clawock/refs/heads/master/site/assets/claude-code-terminal.png
Decision Mind plugin — decision traces: real fills with soft-paired decisions and T+1 verdicts, expandable to a plan → execution → result timeline
https://raw.githubusercontent.com/KCNyu/clawock/refs/heads/master/site/assets/dsh-decision-mind.png
cumulative episode win rate against a 50% directional-hit line
https://raw.githubusercontent.com/KCNyu/clawock/refs/heads/master/site/assets/shadow-backtest.png
clawock — portable investment decision workflows for any external AI agent, proven on a live HK and US desk
https://raw.githubusercontent.com/KCNyu/clawock/refs/heads/master/site/assets/social-card.png
Install
Installation unavailable
This entry is not currently marked as installable.
Tags
README badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/KCNyu/clawock)Related plugins
Development & Runtimedistilly
★ 24153Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）.
MemOS
★ 11085Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
dsh-quant
★ 27Quantitative R&D toolkit for DeepSeek Harness — 46 tools across six domains covering market data, indicators, factor evaluation, walk-forward ML validation, risk, options, bonds and fund simulation, with an end-to-end research pipeline.