v2.13.2 · MIT
"ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness check, penetration testing, code review, competitive analysis, incident response. 1 dependency. 180 tests. MIT.
v3.0.0 · MIT
Session lifecycle management for Claude Code — persistent memory, soul purpose, reconcile, harvest, archive
v0.15.1 · MIT
Task-specific React apps for DeepSeek Harness with state carried into the next Agent turn
v0.3.18 · MIT
In-GUI skill hub for DeepSeek Harness (dsh): browse the full local skill catalog from the official ctx.skills registry (every root + third-party providers), toggle skills on/off, inspect bodies, surface frontmatter diagnostics, and scaffold new skills — p
v0.3.13 · MIT
DeepSeek Harness control center for balance, usage, peak/off-peak pricing, encrypted multi-account switching, health checks, reminders, recharge, and session controls. / 余额、用量、峰谷计费、加密多账户、健康检查、提醒、充值与会话控制
v0.3.19 · Apache-2.0
The dsh-plugin-guide knowledge base plus the dsh-plugin-dev CLI toolchain: official docs, Cordis primer, community deep-dives, and battle-tested pitfalls registered as an on-demand agent skill, with a scaffolder, static checker, and pack verifier for buil
v2.0.0 · MIT
Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.
v1.4.1 · MIT
Editor-facing ACP server for Zed and other ACP clients, composed from published DeepSeek Harness plugins. Community-maintained; not affiliated with DeepSeek.
v3.47.0 · MIT
You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.
v0.5.2 · MIT
Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models
v0.10.169 · Apache-2.0
Your AI forgets everything between sessions. cachly fixes that permanently: 124 MCP tools for Claude Code, Cursor, Copilot & Windsurf. Learns from every bug fix, commit and CI run. Arrives pre-briefed. Free tier forever, EU servers, GDPR.
— · MIT
AI made building cheap. It didn't make deciding cheap. Mycelium is a Claude Code harness that makes your agent run discovery and weigh evidence before it writes code. It earns the right to start. Built for software, courses, AI tools, and services.
v0.42.0 · Apache-2.0
Agentic Version Control System — an AI-native VCS where intent, session, operation, evidence and decision are first-class objects and code is a materialized projection of an operation graph.
v0.1.0 · MIT
Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev as a System One decision layer for agent selection, supervision, corrections, and approvals.
v1.1.66 · no license
Official PostHog plugin for Claude Code, Cursor, Gemini, Codex and other AI coding tools
— · Apache-2.0
Connect your AI agent to the world — Web search, Social media, Crypto & On-chain data. One plugin, zero extra config.
v0.2.1 · MIT
Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.
v0.5.0-alpha.4 · MIT
Automatically turn successful DeepSeek Harness sessions into reusable, reviewable Agent Skills.
v0.6.0 · MIT
Procedural writing-style skills for AI agents: official frameworks (plain language, business writing, GOV.UK, AP style, STE-100, developer docs) + character voices. Agent Plugins 1.0.0, works in opencode, Claude Code, Codex.
— · Apache-2.0
Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
v5.0.2 · MIT
DSH permission-gate for the DeepSeek Harness 0.1.5 line: a single self-sufficient, deterministic-first, fail-closed gate covering P0 hard-deny -> P1 session grant -> P2 static rule (allow/deny) chain -> P3 optional LLM semantic classifier -> P4 ask, with
v0.1.18 · MIT
Mobile client for the DeepSeek Harness — use the dsh on your dev machine from your Android or iOS phone, remotely across networks, peer-to-peer over iroh with no server to set up (falls back to a relay that only sees ciphertext)
v0.0.0 · MIT
DeepSeek Harness adapter for Qwen Token Plan CN with Responses tools, GLM Chat routing, and a versioned official catalog
v0.3.18 · Apache-2.0
:star: AI-assisted development workflow that produces understanding alongside code. Teach, capture decisions, document, assemble reviews.