The "code-review" topic on GitHub groups 57 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by superpowers-zh with 8.1k GitHub stars. superpowers-zh — AI coding superpowers · Chinese enhanced edition — superpowers (250k+ ) fully localized + 4 original Chinese skills, making 26 AI coding tools such as Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI / Qoder actually get work done. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
🦸 AI coding superpowers · Chinese enhanced edition — superpowers (250k+ ⭐) fully localized + 4 original Chinese skills, making 26 AI coding tools such as Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI / Qoder actually get work done
AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix
Agent Skills that teach coding agents to write, review, and port idiomatic Rust, plus a tested clippy config. Works with Claude Code, Codex, Copilot, Cursor, and Gemini CLI.
Delegate bounded coding tasks to a headless WorkBuddy/CodeBuddy CLI agent from DeepSeek Harness — structured result, real diff, path whitelist and worktree isolation.
Open-source AI skills for SEO, AI search visibility, conversion copy, marketing strategy, and business operations. Reusable workflows for Claude Code and Codex, plus code review, app delivery, and creator tools.
One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 33 modes, 6-layer security, 23 hooks, and 75% token savings. Works on Codex, Cursor, Manus, Windsurf.
A safety gate for DeepSeek Harness: a stronger model reviews dangerous tool calls before they run. Plus vision and BlockRun's full model catalog from one wallet, paid per request over x402.
Official-grade GitHub CI for DeepSeek Harness: composite action.yml, PR review bot with idempotent inline comments and a status-check gate, plus PR/issues tools with every write gated by human approval (Apache-2.0, dsh-plugin).
Native interactive Git diff review for DeepSeek Harness with structured annotations sent back to the current Agent session. DeepSeek Harness native interactive Git diff review with structured annotations sent back to the current Agent session.
Renders edit and write tool calls as always-expanded side-by-side git-style diffs in a diff viewer, with optional syntax coloring and word-level highlighting.
Five engineering-discipline skills for AI coding agents (DeepSeek Harness, Claude Code, Codex): 18-dimension code review, CI failure triage, shell safety, redundancy/boundary audit, and cross-repo pattern absorption - pure markdown, no install.
Evidence-first multi-model consultation for DeepSeek Harness: 2–5 independently configured models review the same evidence, and the main agent synthesizes their anonymous opinions.
DeepSeek Harness multi-agent collaborative development plugin with seven built-in agents (Qibo, Lishou, Feng Hou, Kui, Li Mu, Gao Yao, Li Zhu), covering the full development loop of project initialization, code categorization, plan orchestration, batch execution, code review and test verification. Built on the @deepseek-ai/cordis plugin system, giving dsh "Feng Hou & Li Mu"-style multi-agent collaboration.
External-expert consultation for DeepSeek Harness: headless Claude Code CLI with role personas (advisor/reviewer/designer, extensible), replies as reference answers — thinking effort, model fallback, panels, settings workspace. · DSH external expert consultation: headless Claude Code CLI calls, role personas (advisor/reviewer/designer, extensible) reply as reference answers — thinking effort, model fallback, parallel consultation, settings workspace.
/code-review slash command for DeepSeek Harness — five parallel review lenses, per-finding confidence scoring, then a gh reply back on the pull request.
Code-review pack for DeepSeek Harness (dsh): the /review shortcut over the pinned Changes page, plus the dsh-change-review Skill that teaches an agent what a rejected change means.
DSH plugin: a read-only PR and release workspace inside the sidebar — grouped PR lists, diffs, comments, local review notes, and six independent release facts.
Second-opinion review for DeepSeek Harness sessions: a restricted child session re-reads the Executor's work with read-only tools and delivers severity-ranked advice.
DeepSeek Harness plugin: deterministic code-review scope and rule resolution from alibaba/open-code-review, judged by your own DSH model. No API key, no second provider.
A DeepSeek Harness (dsh) plugin for code review: open-code-review (ocr) delegation — deterministic file selection & rule resolution, reviewed by your own model (zero extra API key)
DeepSeek Harness plugin: per-tool-call Auto-permission review powered by TypeSafe Jev, with account usage and API-key management inline on its settings page
A deterministic /review command for DeepSeek Harness: a reviewer subagent pinned to a subscription-backed Codex model, with a settings card, one reviewer session per chat, and /review reset to forget it.