Plugin Claude Code
Plugin marketplace listing 14 plugins: core-config, github-dev, e2e-harness, code-scout, deepwiki.
Personal Claude Code plugin collection: core-config, github-dev, council, code-scout, and more
Plugin Claude Code
Plugin marketplace listing 14 plugins: core-config, github-dev, e2e-harness, code-scout, deepwiki.
Plugin Claude Code
Multi-axis code & ML research harness. 5-axis scout team (github/hf/web/docs/paper) + synthesis-scout + research-orchestrator skill + exa-web-search skill. exa MCP first, WebSearch fallback, brightdata tier-3, insane-search tier-4 (WAF/blocked URLs). paper-scout wraps paper-search-tools 8-source family. /deep-research.
Plugin Claude Code
Claude-only (do not install into Codex). Generate or edit images from Claude Code by delegating to Codex CLI image generation (ChatGPT OAuth, no OpenAI API key). Claude-only bridge; excluded from Codex sync.
Plugin Claude Code
Python auto-format + cross-platform notifications + per-prompt behavioral block (promptinject.sh, shared Claude + Codex). The block is fixed; two pointers are conditional — .llmwiki/insight/ when a knowledge root resolves in cwd, and a one-line [council] delegation reminder when a second-model CLI (codex / agy).
Plugin Claude Code
Claude-only (do not install into Codex). Cross-vendor model council. codex (GPT), agy (Gemini), and a Claude Opus seat answer independently, surface follow-up questions to the user, then rebut each other before the chair synthesizes. Seat models live in a weekly-TTL registry at /.claude/council-models.json. Claude-onl.
Plugin Claude Code
AI-powered GitHub repo documentation. Dual-surface: /deepwiki:ask + /deepwiki:generate-llmstxt commands and matching skills for fuzzy-trigger discovery.
Plugin Claude Code
README/CHANGELOG generation with CRO best practices, plus deployment-doc templates and MOC index generation Also absorbs agent-facing authoring: write-rules (CLAUDE.md + .claude/rules generation), interview-methodology (requirements interview / grill-me stress test), tcrei-prompt (TCREI prompt rewriting), voice-prompt.
Plugin Claude Code
Playwright E2E test-harness engineering — wraps Playwright's official AI test agents (npx playwright init-agents --loop=claude generates planner/generator/healer). Three skills close the planner -> generator -> healer self-improving loop: e2e-setup onboards the full harness (agents, auth separation via storageState +…
Plugin Claude Code
GitHub workflow: commit, PR, issue, worktree, unified CodeRabbit + ChatGPT-Codex cr-fix pipeline v2 (Step 5 pre-flight review detection across CR commit-status + comments + Codex reviews + Codex emoji 3-channel; autonomous Step 9 judgment replaces per-finding AskUserQuestion — LLM judges real/spurious + severity + fix.
Plugin Claude Code
Karpathy LLM-Wiki 3-layer (insight + wiki + raw under neutral .llmwiki/): 5 skills (query/ingest/lint/bootstrap/migrate) + 5 hooks + bootstrap templates. Three soft hints plus an auto-capture/ingest path: a Stop hook mechanically captures ingest candidates to /.staging/ and the next session's SessionStart drain h.