~ / rigs / maycuatroi1 / evo-agents

maycuatroi1/evo-agents

Self-driving agent teams: a hub that runs plans on workers, with a multi-source knowledge graph and Claude Code plugins

↗ GitHub ★ 3 Apache-2.0 updated 1d ago collection Codex Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~14.2k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ claude mcp add evo-hub -- evo-agents hub mcp --sink claude-code@anthropic
$ claude mcp add evo-kg -- evo-agents kg serve --sink claude-code@anthropic
$ claude mcp add playwright -- npx -y @playwright/mcp@0.0.83 --cdp-endpoint ${EVO_BROWSER_CDP}

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.

$ claude mcp add evo-hub -- evo-agents hub mcp --sink claude-code@anthropic
$ claude mcp add evo-kg -- evo-agents kg serve --sink claude-code@anthropic
$ claude mcp add playwright -- npx -y @playwright/mcp@0.0.83 --cdp-endpoint ${EVO_BROWSER_CDP}
$ npx degit maycuatroi1/evo-agents/evo_agents/core_plugins/builder/packs/builder/skills/hub-settings .claude/skills/hub-settings
$ npx degit maycuatroi1/evo-agents/evo_agents/core_plugins/builder/packs/builder/skills/plugin-authoring .claude/skills/plugin-authoring
$ npx degit maycuatroi1/evo-agents/evo_agents<redacted>-editing .claude/skills/canvas-editing
$ npx degit maycuatroi1/evo-agents/evo_agents<redacted>-judging .claude/skills/evidence-judging
$ npx degit maycuatroi1/evo-agents/evo_agents/hub/server/canvas/packs/strategist/skills/lean-canvas .claude/skills/lean-canvas
$ npx degit maycuatroi1/evo-agents/evo_agents/hub/server/srs/packs/ba/skills/srs-review .claude/skills/srs-review
$ npx degit maycuatroi1/evo-agents/evo_agents/hub/server/srs/packs/ba/skills/srs-settle .claude/skills/srs-settle
$ npx degit maycuatroi1/evo-agents/evo_agents/hub/server/srs/packs/ba/skills/srs-tasks .claude/skills/srs-tasks
$ npx degit maycuatroi1/evo-agents/evo_agents/hub/server/srs/packs/ba/skills/srs-writing .claude/skills/srs-writing
$ npx degit maycuatroi1/evo-agents/plugins/evo-hub/skills/answering-curator-proposals .claude/skills/answering-curator-proposals
$ npx degit maycuatroi1/evo-agents/plugins/evo-hub/skills/interactive-answers .claude/skills/interactive-answers
$ npx degit maycuatroi1/evo-agents/plugins/evo-hub/skills/triaging-failed-runs .claude/skills/triaging-failed-runs
$ npx degit maycuatroi1/evo-agents/plugins/evo-hub/skills/using-agent-hub .claude/skills/using-agent-hub
$ npx degit maycuatroi1/evo-agents/plugins/evo-kg/skills/using-project-graph .claude/skills/using-project-graph

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 *)"
    ]
  }
}

MCP servers (3)

serversourceest. tokens
evo-agents · "evo-hub" binary 2.5k
evo-agents · "evo-kg" binary 2.5k
Playwright MCP · "playwright" npm 7.5k

Skills (14)

Similar rigs

copied ✓