~ / rigs / matt82198 / aesop

matt82198/aesop

Orchestration kernel for autonomous software development — crash-only multi-agent coordination on git and plain text, fail-closed verification gates, self-learning guardrails.

↗ GitHub ★ 7 NOASSERTION updated 25d ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~10.7k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
2/5
Pre-tool screening hook · No YOLO mode · details
Quality 34/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit matt82198/aesop/.claude ./rig-aesop  # inspect, then merge into .claude/

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 matt82198/aesop/skills/buildsystem .claude/skills/buildsystem
$ npx degit matt82198/aesop/skills/dashboard .claude/skills/dashboard
$ npx degit matt82198/aesop/skills/fleet .claude/skills/fleet
$ npx degit matt82198/aesop/skills/healthcheck .claude/skills/healthcheck
$ npx degit matt82198/aesop/skills/power .claude/skills/power

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Agent|Task",
        "hooks": [
          {
            "type": "command",
            "command": "node \"$CLAUDE_PROJECT_DIR/hooks/claude/force-model-policy.mjs\""
          }
        ]
      }
    ]
  }
}

Skills (5)

Hooks (1)

eventmatcherruns
PreToolUseAgent|Tasknode "$CLAUDE_PROJECT_DIR/hooks/claude/force-model-policy.mjs"

Similar rigs

copied ✓