cinicu/opencode-dotfiles
OpenCode dotfiles — 19 AI agent skills + 8 MCP servers + persistent memory (memory-keeper). Cross-platform install, screenshot OCR, custom CLI toolchain. Research methodology, systematic reviews, critical analysis, skill-creator.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ npx degit cinicu/opencode-dotfiles/agents ./rig-opencode-dotfiles/agents $ npx degit cinicu/opencode-dotfiles/skills ./rig-opencode-dotfiles/skills
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit cinicu/opencode-dotfiles/skills/7zip .claude/skills/7zip $ npx degit cinicu/opencode-dotfiles/skills/academic-writing .claude/skills/academic-writing $ npx degit cinicu/opencode-dotfiles/skills/caveman .claude/skills/caveman $ npx degit cinicu/opencode-dotfiles/skills/critical-analysis .claude/skills/critical-analysis $ npx degit cinicu/opencode-dotfiles/skills/ethics-review .claude/skills/ethics-review $ npx degit cinicu/opencode-dotfiles/skills/hypothesis-testing .claude/skills/hypothesis-testing $ npx degit cinicu/opencode-dotfiles/skills/lateral-thinking .claude/skills/lateral-thinking $ npx degit cinicu/opencode-dotfiles/skills/literature-review .claude/skills/literature-review $ npx degit cinicu/opencode-dotfiles/skills/memory-logger .claude/skills/memory-logger $ npx degit cinicu/opencode-dotfiles/skills/polish .claude/skills/polish $ npx degit cinicu/opencode-dotfiles/skills/qualitative-research .claude/skills/qualitative-research $ npx degit cinicu/opencode-dotfiles/skills/quantitative-analysis .claude/skills/quantitative-analysis $ npx degit cinicu/opencode-dotfiles/skills/research-manager .claude/skills/research-manager $ npx degit cinicu/opencode-dotfiles/skills/research-methodology .claude/skills/research-methodology $ npx degit cinicu/opencode-dotfiles/skills/research-synthesis .claude/skills/research-synthesis $ npx degit cinicu/opencode-dotfiles/skills/screenshot .claude/skills/screenshot $ npx degit cinicu/opencode-dotfiles/skills/skill-creator .claude/skills/skill-creator $ npx degit cinicu/opencode-dotfiles/skills/systematic-review .claude/skills/systematic-review $ npx degit cinicu/opencode-dotfiles/skills/using-opencode-researcher .claude/skills/using-opencode-researcher
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/cinicu/opencode-dotfiles/main/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/yolo.md https://raw.githubusercontent.com/cinicu/opencode-dotfiles/main/agents/yolo.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (19)
7zipacademic-writingcavemancritical-analysisethics-reviewhypothesis-testinglateral-thinkingliterature-reviewmemory-loggerpolishqualitative-researchquantitative-analysisresearch-managerresearch-methodologyresearch-synthesisscreenshot-captureskill-creatorsystematic-reviewusing-opencode-researcher
Subagents (2)
| researcher | PhD-level research assistant for academic research — literature reviews, critical analysis, hypothesis testing, and scientific writing. Automatically loads appropriate research skills and follows esta |
| yolo | Dangerous mode - allows potentially destructive operations with confirmation |
Similar rigs
eclaflin/claude-dotfiles
Personal Claude Code skills and commands. Portable across machines via symlinks. Includes original, AI-assisted, and open source derived skills.
Pragmatist 678 tok ·
phamquiluan/dotfiles
Long live Linux! Long live Unix!
Pragmatist 465 tok ·
jebadenas/claude-config
Claude Code global configuration: rules, hooks, skills, settings
YOLO Cowboy 614 tok ·
vstorm-co/pydantic-deepagents
Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.
Skill Collector 5.0k tok ·