l123-harness
Three-tier agent memory harness: L1 always-on CLAUDE.md, L2 index, L3 detail skeleton with templates, a gate that blocks writes to protected files without a one-time approval token, zero-judgement event logging, weekly distillation, and a TDD execution-loop skill.
三级记忆 agent 底座:L1 常驻层、L2 索引、L3 详情骨架与模板,受保护文件门禁(一次性审批令牌),零判断事件日志,周审提炼与 TDD 执行流技能。
How to install
dsh plugin add github:reatcat/l123-harness git clone https://github.com/reatcat/l123-harness ~/.claude/skills/l123-harness About
l123-harness —— L1-L2-L3 三级记忆 Agent 底座 把一套经过实战检验的 agent 方法论打包成插件:**Claude Code 插件** + **DeepSeek Harness (dsh) 组合包**,同一套内容双宿主分发。设计对齐「一切皆插件」: **宿主是内核,本插件只提供能力组件**——上下文注入、门禁、事件记录、记忆提炼, 全部可单独理解、可整体装卸。项目知识不在插件里:插件装机后由项目自己积累。 **English** — l123-harness packages a battle-tested agent methodology as a plugin for both Claude Code and DeepSeek Harness (dsh): a three-tier memory system (L1 always-on CLAUDE.md / L2 index / L3 details) plus gate approval for protected files, a zero-judgement event log, weekly distillation, and a TDD execution loop. Install for dsh: dsh plugin --profile web add github:reat…
Recommendation signals
Meta
- License
- MIT
- Language
- Shell
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-08-22
- Created
- 2026-08-22
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- agent-memory, agent-skills, claude-code-plugin, deepseek-harness, dsh-plugin, harness, hooks, methodology, skills, tdd
Related plugins
hindsight
vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
brightdata-mcp
luminati-io/brightdata-mcp
A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.
memsearch
zilliztech/memsearch/tree/main/plugins/dsh
Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.
hivemind
activeloopai/hivemind
Hivemind turns your traces into reusable skills across agents