dokyit/Trek
Every agent. One trail. A native desktop app (Rust + GPUI) for macOS and Windows that runs Claude Code, Codex, OpenCode, Cursor, Copilot and other ACP agents, plus API and local models, from one inbox, with an iPhone companion for approvals
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
$ git clone --depth 1 https://github.com/dokyit/Trek 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 dokyit/Trek/.agents/skills/verify-trek .claude/skills/verify-trek $ npx degit dokyit/Trek/crates/trek-core/skills/create-verification-skill .claude/skills/create-verification-skill $ npx degit dokyit/Trek/crates/trek-core/skills/database-migration-card .claude/skills/database-migration-card $ npx degit dokyit/Trek/crates/trek-core/skills/maintain-verification-skill .claude/skills/maintain-verification-skill $ npx degit dokyit/Trek/crates/trek-core/skills/map-card .claude/skills/map-card $ npx degit dokyit/Trek/crates/trek-core/skills/pull-request-card .claude/skills/pull-request-card $ npx degit dokyit/Trek/crates/trek-core/skills/study .claude/skills/study
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (7)
Similar rigs
justAbdulaziz10/ObsessionSystem
Rules, skills and a delivery gate for Claude Code that make the agent prove its work before anything ships.
Pragmatist 717 tok · · Q0
woodbeary/later-dog
AI agents you talk to like teammates. Free and open source for Mac: dogs with their own files and chat that hand coding work to cloud tasks and open draft pull requests, on your Claude or ChatGPT plan.
Skill Collector 1.2k tok · · Q0
iamenochchirima/estack
Agent skills for reliable autonomous software engineering workflows.
Skill Collector 631 tok · · Q0
The-AIE/the-gibson
A portable, self-improving SDLC harness for agent fleets — plan → issues → build → test → review → UX-eval → security → ship, on any runtime (Claude Code, Codex, Grok, Hermes). Apache-2.0.
Skill Collector 5.7k tok · · Q10