aegis
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
25 results
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
Opt-in DeepSeek Harness Skill-only bundle for the Archify architecture-diagram skill.
Embedded C/C++ firmware development toolbox — 4 agents, 8 skills covering FreeRTOS, ISR, NVM storage, Keil MDK, ARMCLANG, HardFault, state machines, architecture, LVGL patterns, and claim fact-checking. Ships a native DeepSeek Harness (dsh) bundle that injects the session-start gate into the first model step.
SHOPLINE AI Toolkit for DeepSeek Harness (DSH): bridges the official SHOPLINE Developer MCP server and ships SHOPLINE agent skills, mirroring the Shopify AI Toolkit architecture. dsh-plugin.
BrainAgent — brain-inspired plugin for DeepSeek Harness (dsh): a pipeline of heuristic filters, statistical memory stores and context injections; reward-ledger + UCB1 bandit learning loop (RL-lite)
Code reference & reuse-survey plugin for DeepSeek Harness (DSH): search local code + GitHub/npm before building, evaluate reuse vs rewrite, ask the user, architecture-level reuse. 开发前检索本地与开源可复用代码并询问用户的复用调查插件。
LMA (Layered Memory Architecture) 是一个为 DeepSeek Harness 设计的地基插件(Foundation Plugin)。它定义了 “记忆体(Memory Body)” 这一抽象概念及其挂载/卸载协议。 它与其他记忆插件的本质区别在于:LMA 是一个容器和载体,让 dsh-memory-evolve、EchoCore 等“能力性插件”可以挂载其上,它本身也内置了一套可开关的基础记忆流程,作为可选能力。LMA结束记忆功能的“一锅乱炖”,实现跨会话的结构化记忆机制。(目前功能还在持续完善以及测试,对于其他插件的接口在构想完整后逐步推动)
Agent-driven kanban board plugin for DeepSeek Harness: one board per workspace, per-task agent sessions, human/agent workflow guards, light/dark UI. Based on the dsh-kanban plugin architecture.
DeepSeek Harness plugin: the agent publishes a project plan (steps) and a project framework (architecture graph); the browser renders the steps in a right-hand panel and the framework as a downloadable diagram in the center view.
Evidence-driven system architecture reconnaissance for DeepSeek Harness
MEMFLOW memory framework for DeepSeek Harness — distributed memory architecture: every project carries its own memory/, one plugin for Hermes-like memory across all your workflows
架构模式:Clean Architecture、Hexagonal、DDD 战术模式、依赖规则。受 wshobson/agents(38k★ MIT)启发。
理解任何东西技能包(移植自 Understand-Anything)
DSH arch-doc skill plugin: analyze a codebase and generate architecture documentation (module responsibilities, dependencies, entry points and run methods).
云 Well-Architected 六支柱评审框架:可靠性(用户经验目标/SLO/冗余/水平扩展/可观测性/优雅降级/恢复测试/无指责复盘)、成本优化、运维卓越、性能优化、安全、可持续性——设计原则+建议驱动架构评估与改进。受 google/skills(18.5k★ Apache-2.0)启发。
DSH arch-doc skill plugin: analyze a codebase and generate architecture documentation (module responsibilities, dependencies, entry points and run methods).
Clean Architecture 参考库(agent 审查基线): 8 仓钉版 FTS5 搜索 + 断言清单 + 自动审查台账 + 只读观察窗
Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval
Embedded C/C++ firmware development toolbox — 4 agents, 7 skills covering FreeRTOS, ISR, NVM storage, Keil MDK, ARMCLANG, HardFault, state machines, architecture, and LVGL patterns. Ships a native DeepSeek Harness (dsh) bundle that injects the session-start gate into the first model step.
DSH bundle (组合包): read-only project knowledge graph — modules, tech stack, architecture layers, file-level import graphs, observations. Provides /kgraph command, project_kgraph model tool and a browser UI panel.
Shengyv Writing Architecture 提示词优化:主框 ✨ 一键意图感知改写;C 方案复刻完整会话命中 prompt cache;CAS 写回;trace 落盘;sidebar 事件总线联动
文档与架构决策记录:记录为什么而非只是什么,ADR 格式与文档策略。受 addyosmani/agent-skills(88k★ MIT)启发。
SQL 优化模式:EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents(38k★ MIT)启发。
dsh-arch-advisor: an in-chat architecture consultant for DeepSeek Harness — 7 tools querying the awesome-architecture knowledge base (tutorials/templates/cases) plus engineering-doc standards. · DeepSeek Harness 架构顾问插件:7 个 arch_* 工具查询 awesome-architecture 知识库,并附开发文档规范。