Ultragoal Workflow
SkillDev toolsultragoal is a skill for AI agents that turns a short brief into a durable multi-goal plan stored as files inside the repository. It then executes each goal in sequence using Codex goal mode commands, verifying finished work against real artifacts and blocking completion until code review and invariant checks pass.
Use Ultragoal Workflow in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Ultragoal Workflow and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Ultragoal Workflow skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
No other account needed.
Have an AI agent that supports skills and Codex goal mode commands.
What your AI can do with it
- Turn a short brief into a durable multi-goal plan stored as repo files
- Execute each goal in sequence with Codex goal mode commands
- Use create-goals, complete-goals, and checkpoint commands
- Verify each finished story against real artifacts
- Support structured steering such as adding or reordering subgoals
- Block completion until code review and invariant checks pass
Getting started
- Have an AI agent that supports skills and Codex goal mode commands.
- Add the ultragoal skill to that agent.
- Give the agent a short brief for the coding work you want planned.
- Let the agent create the multi-goal plan as files inside the repository.
- Run the plan so the agent executes each goal in sequence.
What this skill tells your AI
The instructions your AI receives, as published by yeachan-heo/oh-my-codex in skills/ultragoal/SKILL.md and read by ahel’s review.
When to use
Use for ultragoal, create-goals, complete-goals, durable multi-goal planning, or sequential execution over Codex /goal. Read AGENTS.md#durable-runtime-invariants-canonical-ssot for state ownership and goal-tool boundaries.
Inputs and preconditions
- Durable artifacts are
.omx/ultragoal/brief.md,.omx/ultragoal/goals.json, and.omx/ultragoal/ledger.jsonl. - New plans use aggregate Codex goal mode by default: one stable pointer objective for the plan while OMX tracks individual stories. Use
--codex-goal-mode per-storyonly when explicitly requested. - Do not call
/goal clearfrom shell or this skill. After a completed run, the operator may clear the interactive Codex goal in the Codex UI before another same-thread run.
Operational steps: create
Run one command, then inspect the generated plan:
omx ultragoal create-goals --brief "<brief>"
omx ultragoal create-goals --brief-file <path>
cat <brief> | omx ultragoal create-goals --from-stdin
omx ultragoal create-goals --codex-goal-mode per-story --brief "<brief>"
If refinement is needed, use explicit supported steering rather than editing durable artifacts by hand.
Operational steps: execute
Repeat until omx ultragoal status reports all goals complete:
- Run
omx ultragoal complete-goalsand read its handoff. - Call
get_goal. Callcreate_goalwith the printed payload only when no active Codex goal exists; otherwise continue the matching aggregate objective. - Complete one OMX story and audit its objective against real artifacts and verification evidence.
- For intermediate aggregate stories, keep the Codex goal active and checkpoint:
omx ultragoal checkpoint --goal-id <id> --status complete --evidence "<evidence>" --codex-goal-json <fresh-get-goal-json-or-path> - For a blocked/failed story, use
--status blocked|failedwith evidence; resume failed work withomx ultragoal complete-goals --retry-failed. - On the final story, complete the final gate below before
update_goal({status: "complete"}); then callget_goalagain and checkpoint the fresh complete snapshot.
Explicit steering
Use evidence-backed directives only when the decomposition must change:
omx ultragoal steer --kind add_subgoal --title "<title>" --objective "<objective>" --evidence "<evidence>" --rationale "<reason>" --json
omx ultragoal steer --directive-json ./steering.json --json
Supported kinds: add_subgoal, split_subgoal, reorder_pending, revise_pending_wording, annotate_ledger, and mark_blocked_superseded. Ordinary prose does not mutate the plan; repeated structured directives dedupe.
Phase/HUD handoff
At standalone activation, declare the smallest accurate phase (planning, executing, verifying, reviewing, checkpointing, or blocked):
omx state write --input '{"mode":"ultragoal","active":true,"current_phase":"planning"}' --json
Inside Autopilot, keep the parent mode active and set current_phase:"ultragoal"; persist Ultragoal evidence under handoff_artifacts.ultragoal before a code-review handoff. Mark standalone Ultragoal complete only when every durable goal is complete.
Optional Team bridge
For parallel story execution, use the separate Team command. The leader records the Ultragoal checkpoint with a fresh get_goal snapshot; see the Team skill for the bridge details.
Final gate and exit evidence
Before final completion:
- Run targeted story verification.
- Run
ai-slop-cleaneron changed files, then rerun verification. - Audit every architecture/domain invariant from the brief/spec/accepted steering against implementation, test, and review evidence.
- Run
$code-reviewthrough independentcode-reviewerandarchitectlanes. If review or invariant proof is not clean, do not update the Codex goal; record durable blockers:omx ultragoal record-review-blockers --goal-id <id> --title "Resolve final code-review blockers" --objective "<objective>" --evidence "<findings>" --codex-goal-json <active-get-goal-json-or-path> - If clean, call
update_goal({status: "complete"}), callget_goal, and checkpoint with--quality-gate-jsoncontaining cleaner, verification, review, and architecture-invariant evidence.
Report goal ids/statuses, ledger/checkpoint paths, fresh goal snapshot evidence, review verdicts, and any blocker. Never claim completion from OMX state alone.
Signals
- GitHub stars
- 33k
- Forks
- 3k
- Last commit
- Oct 2026
Questions
- Where is the multi-goal plan stored?
- The plan is stored as files inside the repository, so it stays with the code.
- What commands does it use to execute goals?
- It uses Codex goal mode commands including create-goals, complete-goals, and checkpoint.
- Can I change the plan while it is running?
- Yes. It supports structured steering such as adding or reordering subgoals.
- How does it know a goal is finished?
- It verifies each finished story against real artifacts and blocks completion until code review and invariant checks pass.
- Does it work without Codex goal mode?
- No. It executes goals using Codex goal mode commands, so that support is required.
Advanced
- Item type
- skill
- Key
ultragoal-2- Source
- github.com/yeachan-heo/oh-my-codex
github.com/yeachan-heo/oh-my-codex