ultragoal
Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.
Best for systematic multi-step proje…Works with GitHubLow risk
⌘source
- author
@Yeachan-Heo- language
- TypeScript
★28kstars
2.2kforks
May 6, 2026
✦overview.md
Key Features
- ·Durable multi-goal plans
- ·Repo-native artifacts
- ·Sequential goal execution
- ·Checkpoint with ledger
Use Cases
- →Breaking a large task into sequential goals
- →Tracking progress across multiple Codex goals
- →Reproducible planning with version-controlled artifacts
Best for
- ✓systematic multi-step projects
- ✓goal-oriented workflows
Not ideal for
- !ad-hoc single tasks
FAQs
name
ultragoal
description
Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.
Ultragoal Workflow
Use when the user asks for ultragoal, create-goals, complete-goals, durable multi-goal planning, or sequential execution over Codex /goal.
Purpose
ultragoal turns a brief into repo-native artifacts and then drives one goal at a time through Codex goal tools:
.omx/ultragoal/brief.md.omx/ultragoal/goals.json.omx/ultragoal/ledger.jsonl
Create goals
- Run one of:
omx ultragoal create-goals --brief "<brief>"omx ultragoal create-goals --brief-file <path>cat <brief> | omx ultragoal create-goals --from-stdin
- Inspect
.omx/ultragoal/goals.jsonand refine if needed.
Complete goals
Loop until omx ultragoal status reports all goals complete:
- Run
omx ultragoal complete-goals. - Read the printed handoff.
- Call
get_goal. - If no active Codex goal exists, call
create_goalwith the printed payload. - Complete that single goal only.
- Run a completion audit against the objective and real artifacts/tests.
- When complete, call
update_goal({status: "complete"}), then callget_goalagain for a fresh completion snapshot. - Checkpoint the durable ledger with that snapshot:
$install
1-click copynpx skills add Yeachan-Heo/oh-my-codex --skill ultragoalSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
4/ 5
highMostly actionable with clear steps; only a few small gaps remain.