agentrigs
+ submit rig
~ / rigs / guess-guess-who-i-am / llm-task-tree

guess-guess-who-i-am/llm-task-tree

Local-first visual task graph that keeps humans and AI agents aligned on goals, progress, reasoning, and the next action.

↗ GitHub ★ 1 MIT updated today project CodexCursor Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~5.4k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit guess-guess-who-i-am/llm-task-tree/skills ./rig-llm-task-tree/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 guess-guess-who-i-am/llm-task-tree/e2e-simulation/beauty-frontend-demo/llm-task-tree/skills/task-tree-grill .claude/skills/task-tree-grill
$ npx degit guess-guess-who-i-am/llm-task-tree/llm-task-tree-kit/skills/task-tree-chain-run .claude/skills/task-tree-chain-run
$ npx degit guess-guess-who-i-am/llm-task-tree/llm-task-tree-kit/skills/task-tree-core-state .claude/skills/task-tree-core-state
$ npx degit guess-guess-who-i-am/llm-task-tree/llm-task-tree-kit/skills/ta<redacted> .claude/skills/ta<redacted>
$ npx degit guess-guess-who-i-am/llm-task-tree/marketplace/plugins/task-tree/skills/task-tree .claude/skills/task-tree

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 *)"
    ]
  }
}

MCP servers (1)

serversourceest. tokens
task_tree local / custom 2.5k

Skills (5)

task-tree-grilltask-tree-chain-runtask-tree-core-stateta<redacted>task-tree

Cursor rules (2)

llm-task-tree-editllm-task-tree-flow-edit

Similar rigs

ArcanEdge-AI/coding-agent-playbook-codex
An open-source engineering operating model for Codex: model-aware subagents, bounded delegation, task graphs, independent review, and validation.
★ 3 project Codex 10 skills 5d ago
Skill Collector 2.3k tok ·
ArcanEdge-AI/coding-agent-playbook-claude-code
Installable, managed global instructions, subagents, skills, and engineering workflows for Claude Code.
★ 0 project Claude Code 10 skills 6 agents 11d ago
Orchestrator 6.3k tok ·
ragnarwestad/aide
Spec-driven development for AI coding assistants (Claude Code, Codex, OpenCode, Copilot) — specs, skills and a dashboard that runs them.
★ 1 project Claude CodeCodex 25 skills today
Skill Collector 6.6k tok ·
raphaeltm/simple-agent-manager
Run multiple coding agents in parallel on your own cloud VMs.
★ 60 project Claude CodeCodex 1 mcp 16 skills 11 agents today
YOLO Cowboy 11.9k tok ·
copied ✓