Task Orchestrator logo

Task Orchestrator

Community
jdrhyne
task-orchestrator

Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring. Use for large projects with multiple issues/tasks that need coordinated parallel execution.

Overview

Publisherjdrhyne
Repositoryagent-skills
Skill nametask-orchestrator
Stars
240
Forks
30
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jdrhyne on GitHub. Read the source before you install it.

Installation

Install the Task Orchestrator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jdrhyne/agent-skills.git /tmp/agent-skills
mkdir -p .claude/skills
cp -r /tmp/agent-skills/skills/task-orchestrator .claude/skills/task-orchestrator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Task Orchestrator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Task Orchestrator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Task Orchestrator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Task Orchestrator

Autonomous orchestration of multi-agent builds using tmux + Codex with self-healing monitoring.

Load the senior-engineering skill alongside this one for engineering principles.

Safety Boundaries

  • Do not launch parallel workers for tasks with overlapping write scope until the dependency is resolved.
  • Do not push branches, merge work, or self-heal by guessing when human review is required.
  • Do not store secrets in manifests, logs, prompts, or tmux pane captures.
  • Do not continue retrying a failing task indefinitely; stop and surface the blocker after bounded retries.

Core Concepts

1. Task Manifest

A JSON file defining all tasks, their dependencies, files touched, and status.

json
{
  "project": "project-name",
  "repo": "owner/repo",
  "workdir": "/path/to/worktrees",
  "created": "2026-01-17T00:00:00Z",
  "model": "gpt-5.2-codex",
  "modelTier": "high",
  "phases": [
    {
      "name": "Phase 1: Critical",
      "tasks": [
        {
          "id": "t1",
          "issue": 1,
          "title": "Fix X",
          "files": ["src/foo.js"],
          "dependsOn": [],
          "status": "pending",
          "worktree": null,
          "tmuxSession": null,
          "startedAt": null,
          "lastProgress": null,
          "completedAt": null,
          "prNumber": null
        }
      ]
    }
  ]
}

2. Dependency Rules

  • Same file = sequential — Tasks touching the same file must run in order or merge
  • Different files = parallel — Independent tasks can run simultaneously
  • Explicit depends = waitdependsOn array enforces ordering
  • Phase gates — Next phase waits for current phase completion

3. Execution Model

  • Each task gets its own git worktree (isolated branch)
  • Each task runs in its own tmux session
  • Use Codex with --yolo for autonomous execution
  • Model: GPT-5.2-codex high (configurable)

Setup Commands

Initialize Orchestration

bash
# 1. Create working directory
WORKDIR="${TMPDIR:-/tmp}/orchestrator-$(date +%s)"
mkdir -p "$WORKDIR"

# 2. Clone repo for worktrees
git clone https://github.com/OWNER/REPO.git "$WORKDIR/repo"
cd "$WORKDIR/repo"

# 3. Create tmux socket
SOCKET="$WORKDIR/orchestrator.sock"

# 4. Initialize manifest
cat > "$WORKDIR/manifest.json" << 'EOF'
{
  "project": "PROJECT_NAME",
  "repo": "OWNER/REPO",
  "workdir": "WORKDIR_PATH",
  "socket": "SOCKET_PATH",
  "created": "TIMESTAMP",
  "model": "gpt-5.2-codex",
  "modelTier": "high",
  "phases": []
}
EOF

Analyze GitHub Issues for Dependencies

bash
# Fetch all open issues
gh issue list --repo OWNER/REPO --state open --json number,title,body,labels > issues.json

# Group by files mentioned in issue body
# Tasks touching same files should serialize

Create Worktrees

bash
# For each task, create isolated worktree
cd "$WORKDIR/repo"
git worktree add -b fix/issue-N "$WORKDIR/task-tN" main

Launch Tmux Sessions

bash
SOCKET="$WORKDIR/orchestrator.sock"

# Create session for task
tmux -S "$SOCKET" new-session -d -s "task-tN"

# Launch Codex (uses gpt-5.2-codex with reasoning_effort=high from ~/.codex/config.toml)
# Note: Model config is in ~/.codex/config.toml, not CLI flag
tmux -S "$SOCKET" send-keys -t "task-tN" \
  "cd $WORKDIR/task-tN && codex --yolo 'Fix issue #N: DESCRIPTION. Run tests, commit with good message, push to origin.'" Enter

Monitoring & Self-Healing

Progress Check Script

bash
#!/bin/bash
# check_progress.sh - Run via heartbeat

WORKDIR="$1"
SOCKET="$WORKDIR/orchestrator.sock"
MANIFEST="$WORKDIR/manifest.json"
STALL_THRESHOLD_MINS=20

check_session() {
  local session="$1"
  local task_id="$2"
  
  # Capture recent output
  local output=$(tmux -S "$SOCKET" capture-pane -p -t "$session" -S -50 2>/dev/null)
  
  # Check for completion indicators
  if echo "$output" | grep -qE "(All tests passed|Successfully pushed|❯ $)"; then
    echo "DONE:$task_id"
    return 0
  fi
  
  # Check for errors
  if echo "$output" | grep -qiE "(error:|failed:|FATAL|panic)"; then
    echo "ERROR:$task_id"
    return 1
  fi
  
  # Check for stall (prompt waiting for input)
  if echo "$output" | grep -qE "(\? |Continue\?|y/n|Press any key)"; then
    echo "STUCK:$task_id:waiting_for_input"
    return 2
  fi
  
  echo "RUNNING:$task_id"
  return 0
}

# Check all active sessions
for session in $(tmux -S "$SOCKET" list-sessions -F "#{session_name}" 2>/dev/null); do
  check_session "$session" "$session"
done

Self-Healing Actions

When a task is stuck, the orchestrator should:

  1. Waiting for input → Send appropriate response

    bash
    tmux -S "$SOCKET" send-keys -t "$session" "y" Enter
  2. Error/failure → Capture logs, analyze, retry with fixes

    bash
    # Capture error context
    tmux -S "$SOCKET" capture-pane -p -t "$session" -S -100 > "$WORKDIR/logs/$task_id-error.log"
    
    # Kill and restart with error context
    tmux -S "$SOCKET" kill-session -t "$session"
    tmux -S "$SOCKET" new-session -d -s "$session"
    tmux -S "$SOCKET" send-keys -t "$session" \
      "cd $WORKDIR/$task_id && codex --model gpt-5.2-codex-high --yolo 'Previous attempt failed with: $(cat error.log | tail -20). Fix the issue and retry.'" Enter
  3. No progress for 20+ mins → Nudge or restart

    bash
    # Check git log for recent commits
    cd "$WORKDIR/$task_id"
    LAST_COMMIT=$(git log -1 --format="%ar" 2>/dev/null)
    
    # If no commits in threshold, restart

Heartbeat Cron Setup

bash
# Add to cron (every 15 minutes)
cron action:add job:{
  "label": "orchestrator-heartbeat",
  "schedule": "*/15 * * * *",
  "prompt": "Check orchestration progress at WORKDIR. Read manifest, check all tmux sessions, self-heal any stuck tasks, advance to next phase if current is complete. Do NOT ping human - fix issues yourself."
}

Workflow: Full Orchestration Run

Step 1: Analyze & Plan

bash
# 1. Fetch issues
gh issue list --repo OWNER/REPO --state open --json number,title,body > /tmp/issues.json

# 2. Analyze for dependencies (files mentioned, explicit deps)
# Group into phases:
# - Phase 1: Critical/blocking issues (no deps)
# - Phase 2: High priority (may depend on Phase 1)
# - Phase 3: Medium/low (depends on earlier phases)

# 3. Within each phase, identify:
# - Parallel batch: Different files, no deps → run simultaneously
# - Serial batch: Same files or explicit deps → run in order

Step 2: Create Manifest

Write manifest.json with all tasks, dependencies, file mappings.

Step 3: Launch Phase 1

bash
# Create worktrees for Phase 1 tasks
for task in phase1_tasks; do
  git worktree add -b "fix/issue-$issue" "$WORKDIR/task-$id" main
done

# Launch tmux sessions
for task in phase1_parallel_batch; do
  tmux -S "$SOCKET" new-session -d -s "task-$id"
  tmux -S "$SOCKET" send-keys -t "task-$id" \
    "cd $WORKDIR/task-$id && codex --model gpt-5.2-codex-high --yolo '$PROMPT'" Enter
done

Step 4: Monitor & Self-Heal

Heartbeat checks every 15 mins:

  1. Poll all sessions
  2. Update manifest with progress
  3. Self-heal stuck tasks
  4. When all Phase N tasks complete → launch Phase N+1

Step 5: Create PRs

bash
# When task completes successfully
cd "$WORKDIR/task-$id"
git push -u origin "fix/issue-$issue"
gh pr create --repo OWNER/REPO \
  --head "fix/issue-$issue" \
  --title "fix: Issue #$issue - $TITLE" \
  --body "Closes #$issue

## Changes
[Auto-generated by Codex orchestrator]

## Testing
- [ ] Unit tests pass
- [ ] Manual verification"

Step 6: Cleanup

bash
# After all PRs merged or work complete
tmux -S "$SOCKET" kill-server
cd "$WORKDIR/repo"
for task in all_tasks; do
  git worktree remove "$WORKDIR/task-$id" --force
done
rm -rf "$WORKDIR"

Manifest Status Values

StatusMeaning
pendingNot started yet
blockedWaiting on dependency
runningCodex session active
stuckNeeds intervention (auto-heal)
errorFailed, needs retry
completeDone, ready for PR
pr_openPR created
mergedPR merged

Example: Security Framework Orchestration

json
{
  "project": "nuri-security-framework",
  "repo": "jdrhyne/nuri-security-framework",
  "phases": [
    {
      "name": "Phase 1: Critical",
      "tasks": [
        {"id": "t1", "issue": 1, "files": ["ceo_root_manager.js"], "dependsOn": []},
        {"id": "t2", "issue": 2, "files": ["ceo_root_manager.js"], "dependsOn": ["t1"]},
        {"id": "t3", "issue": 3, "files": ["workspace_validator.js"], "dependsOn": []}
      ]
    },
    {
      "name": "Phase 2: High",
      "tasks": [
        {"id": "t4", "issue": 4, "files": ["kill_switch.js", "container_executor.js"], "dependsOn": []},
        {"id": "t5", "issue": 5, "files": ["kill_switch.js"], "dependsOn": ["t4"]},
        {"id": "t6", "issue": 6, "files": ["ceo_root_manager.js"], "dependsOn": ["t2"]},
        {"id": "t7", "issue": 7, "files": ["container_executor.js"], "dependsOn": []},
        {"id": "t8", "issue": 8, "files": ["container_executor.js", "egress_proxy.js"], "dependsOn": ["t7"]}
      ]
    }
  ]
}

Parallel execution in Phase 1:

  • t1 and t3 run in parallel (different files)
  • t2 waits for t1 (same file)

Parallel execution in Phase 2:

  • t4, t6, t7 can start together
  • t5 waits for t4, t8 waits for t7

Tips

  1. Always use GPT-5.2-codex high for complex work: --model gpt-5.2-codex-high
  2. Clear prompts — Include issue number, description, expected outcome, test instructions
  3. Atomic commits — Tell Codex to commit after each logical change
  4. Push early — Push to remote branch so progress isn't lost if session dies
  5. Checkpoint logs — Capture tmux output periodically to files
  6. Phase gates — Don't start Phase N+1 until Phase N is 100% complete
  7. Self-heal aggressively — If stuck >10 mins, intervene automatically
  8. Browser relay limits — If CDP automation is blocked, use iframe batch scraping or manual browser steps

Integration with Other Skills

  • senior-engineering: Load for build principles and quality gates
  • coding-agent: Reference for Codex CLI patterns
  • github: Use for PR creation, issue management

Lessons Learned (2026-01-17)

Codex Sandbox Limitations

When using codex exec --full-auto, the sandbox:

  • No network accessgit push fails with "Could not resolve host"
  • Limited filesystem — Can't write to paths like ~/nuri_workspace

Heartbeat Detection Improvements

The heartbeat should check for:

  1. Shell prompt idle — If tmux pane shows username@hostname path %, worker is done
  2. Unpushed commitsgit log @{u}.. --oneline shows commits not on remote
  3. Push failures — Look for "Could not resolve host" in output

When detected, the orchestrator (not the worker) should:

  1. Push the commit from outside the sandbox
  2. Create the PR via gh pr create
  3. Update manifest and notify

Recommended Pattern

bash
# In heartbeat, for each task:
cd /tmp/orchestrator-*/task-tN
if tmux capture-pane shows shell prompt; then
  # Worker finished, check for unpushed work
  if git log @{u}.. --oneline | grep -q .; then
    git push -u origin HEAD
    gh pr create --title "$(git log --format=%s -1)" --body "Closes #N" --base main
  fi
fi

Frequently asked questions

What does the Task Orchestrator AI skill do?

Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring. Use for large projects with multiple issues/tasks that need coordinated parallel execution.

Why use Task Orchestrator on TypingMind?

Because you install it once and use it with any model. Task Orchestrator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Task Orchestrator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jdrhyne/agent-skills/tree/main/skills/task-orchestrator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Task Orchestrator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Task Orchestrator?

As many as you like. As long as a model supports skills, you can use Task Orchestrator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Task Orchestrator AI skill free?

Yes. It is published on GitHub by jdrhyne under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇