aegis
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
56 results
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
The strongest free web search plugin for coding agents. Plug-in web search, X search, and page fetch for models without native web access. Free out of the box: no signup, no API key (Firecrawl keyless, 1,000 free credits/month)
Standalone OpenTelemetry GenAI observability plugin for DeepSeek Harness
Bring any file into the conversation — stashed to the workspace and referenced by path; zero type rejection
Tencent Cloud Service CLS observability plugin for DeepSeek Harness — direct upload to Tencent Cloud CLS
Agent Client Protocol (ACP) server plugin for the DeepSeek Harness (dsh) — drive dsh agents from Zed and any ACP client
SpecWave — multi-host coding CLI (Cursor/Claude/DSH) + P0 gates/Harness. Formerly SpecGate / dsh-coding-kit. npx spec-wave
Agent Client Protocol (ACP) JSON-RPC stdio server for DeepSeek Harness — bridges Zed and other IDEs to dsh agents
Use Grok Build as an ACP-powered root agent inside DeepSeek Harness Web
DSH encoding tool plugin
Run Pi extensions as agent-scoped DeepSeek Harness plugins
DeepSeek Harness math animation plugin powered by Manim CE (zero-code skills for math/physics users)
Agent negative-knowledge ledger for DeepSeek Harness: records failed paths with evidence hashes and retry conditions, auto-invalidates on evidence change.
Structural code MCP server and batch CLI for compact TypeScript/JavaScript reads and hash-bound AST edits.
生物信息学「许愿式分析」插件:Python 执行器(bio_python:Biopython 全功能 + 出版级绘图)+ 48 个高频语义化工具(差异表达/GSEA、代谢建模/FBA、合成生物学设计、CRISPR、ML、文献检索等)+ 47 个 skill(1 主 skill + 17 领域配方 + 17 协议 + 4 研究方法 + 8 agent 指南)+ 零依赖自举 Python 环境(uv+venv 自动下载到插件私有目录)。用户下载安装即可许愿式分析。
WakaTime plugin for DeepSeek Harness (dsh) — track AI coding activity, lines of code, and time spent
Automated unit-test generation for DeepSeek Harness: a /testgen command and generate_tests tool that scaffold, run, and fix tests until they pass.
项目文档体系初始化 skill(DeepSeek Harness 插件包 / Reasonix 技能):提问驱动落实文档规范 + 固化 AI 协作工作流,以「存量完善」为核心场景,跨平台可用(DSH / Reasonix / Claude Code / Codex)。
Codex-inspired planning, evidence, goal, and anti-loop policy plugin for DeepSeek Harness.
Project-level direction, boundary, and reuse governance for AI coding agents.
Content-aware tool output compression for DeepSeek Harness.
古法编程模式(Classical Programming Mode):AI 只出骨架、用户补全实现、AI 验收讲解的趣味编程练习模式。DeepSeek Harness 双面插件包(Host + Client)+ 随包 Agent 预设组合。
Claude-Code style CLI scheduling bundle for DeepSeek Harness headless: --append-prompt, --resume, --continue, --output-format json, and model overrides.
MCP adapter for DeepSeek Harness — one proxy tool instead of dumping every MCP schema into context.