ultragoal
A tool to track, checkpoint, and verify completion of complex coding objectives through persistent state management.
Install
mkdir -p .claude/skills/ultragoal && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10436" && unzip -o skill.zip -d .claude/skills/ultragoal && rm skill.zipInstalls to .claude/skills/ultragoal
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Durable multi-goal workflow with MCP-backed goal status, checkpoints, and completion evidence. Activate when: ultragoal, goal loop, durable goal, persistent goal, keep goal.Key capabilities
- →Create persistent goal objectives
- →Track progress through milestone checkpoints
- →Maintain goal state in a ledger
- →Verify goal completion with evidence
How it works
The tool maintains a persistent ledger of goals and checkpoints, requiring explicit evidence submission at each milestone before final completion.
Inputs & outputs
When to use ultragoal
- →Tracking progress on multi-step refactoring tasks
- →Documenting evidence for complex feature implementations
- →Maintaining task focus across multiple AI coding sessions
About this skill
Ultragoal
OMG adapted scope: OMG does not use Claude Code goal commands or hidden dynamic prompt injection. Durable goal context is carried through MCP tools and the visible task plan.
Workflow
- Create or inspect the active goal with
omg_ultragoal_status. - If no active goal exists, create one with
omg_ultragoal_createusing a concrete objective. - Keep the active goal reflected in the chat/task TODO state.
- After each meaningful milestone, call
omg_ultragoal_checkpointwith concrete evidence. - Before stopping, call
omg_ultragoal_statusand verify the active goal state. - Complete the goal only with
omg_ultragoal_completeand final evidence.
Fail-Closed Rules
- Missing objective, invalid goal id, malformed ledger, or missing evidence must not write artifacts.
- Use
.omg/ultragoal/artifacts only. - Do not use OMC-only runtime assumptions as execution requirements.
Output
- Active goal id and objective
- Handoff text
- Checkpoint evidence
- Remaining work or completion evidence
When not to use it
- →Tasks lacking a concrete objective
- →Situations where evidence cannot be provided
Limitations
- →Must use .omg/ultragoal/ artifacts only
- →Cannot write artifacts if objective or evidence is missing
How it compares
It enforces a structured, fail-closed workflow for tracking long-term objectives compared to informal task lists.
Compared to similar skills
ultragoal side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ultragoal (this skill) | 0 | 3mo | No flags | Beginner |
| autonomous-agents | 10 | 6mo | No flags | Advanced |
| agent-goal-planner | 2 | 6mo | No flags | Advanced |
| planner | 1 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jmstar85
View all by jmstar85 →You might also like
autonomous-agents
davila7
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b
agent-goal-planner
ruvnet
Agent skill for goal-planner - invoke with $agent-goal-planner
planner
solatis
Interactive planning and execution for complex tasks. Use when user asks to use or invoke planner skill.
hierarchical-coordinator
MadAppGang
Prevent goal drift in long-running multi-agent workflows using a coordinator agent that validates outputs against original objectives at checkpoints. Use when orchestrating 3+ agents, multi-phase features, complex implementations, or any workflow where agents may lose sight of original requirements. Trigger keywords - "hierarchical", "coordinator", "anti-drift", "checkpoint", "validation", "goal-alignment", "decomposition", "phase-gate", "shared-state", "drift detection".
workflow-router
parcadei
Goal-based workflow orchestration - routes tasks to specialist agents based on user goals
loki-mode
davila7
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.