Agent skill

Ultragoal

by jxnl in jxnl/personal-monorepo-template

Design, critique, set, create, activate, or run durable Codex goals for persistent or long-running objectives.

No licenceAuto-check passedAgent Workflows

Install Ultragoal

skills CLI
$ npx skills add jxnl/personal-monorepo-template --skill ultragoal -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jxnl/personal-monorepo-template ultragoal --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jxnl/personal-monorepo-template.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/ultragoal .claude/skills/ultragoal && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ultragoal
GitHub stars
563
Token cost
~1.8k tokens
SKILL.md length
921 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
None found

At a glance

Design, critique, set, create, activate, or run durable Codex goals for persistent or long-running objectives.

  • Works in 7 steps: Ground the Outcome → Research Enough → Check Goal Fit → …
  • The user says set a goal
  • SKILL.md covers Modes, Default Activation Rule, Workflow and Goal Packet, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ultragoal is an agent skill from jxnl/personal-monorepo-template. Design, critique, set, create, activate, or run durable Codex goals for persistent or long-running objectives. Use when the user says "set a goal", "start a goal", "activate goal mode", "persistent goal", "long-running objective", "goal tree", or asks for a goal with verifiers, durable state, approval gates, completion proof, bounded delegation, or parent/child subagent goals.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Design review and critique and Subagents.

When your agent uses it

  • The user says set a goal
  • Activate goal mode
  • Persistent goal
  • Long-running objective

Example prompts

  • “set a goal”
  • “start a goal”
  • “activate goal mode”
  • “/ultragoal”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Ground the Outcome
  2. Research Enough
  3. Check Goal Fit
  4. Define the Loop
  5. Keep State Durable
  6. Delegate Carefully
  7. Activate Last

What it can do on your machine

Read from SKILL.md and the folder at commit df86376. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ultragoal loads about 1.8k tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 921 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 921 words (~1,805 tokens).

“Use this skill when a user wants a persistent Codex goal, not just a longer task. A good goal has an observable finish line, a verifier that can fail, and enough context for Codex to recover after interruptions.”

— opening of SKILL.md by jxnl
name
ultragoal
last_edited
2026-06-15

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .codex/skills/ultragoal of jxnl/personal-monorepo-template.

Open the folder on GitHubat commit df86376

Compare with similar skills

Ultragoal next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ultragoal compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ultragoal this skilljxnl/personal-monorepo-template563—~1.8kAutomated safety check: PassNone
Architecture Design Reviewbbartling/open-fdd173—~1.3kAutomated safety check: PassCustom licence
Personal Assistant Reviewedonyzpc/personal-assistant147—~3.2kAutomated safety check: PassAGPL-3.0
Azsdk Common Pipeline TroubleshootingAzure/azure-sdk-for-android121—~496Automated safety check: PassMIT
LLM Councilffroliva/gflow-cli278—~2kAutomated safety check: PassMIT
Product Designqf-studio/navigator355—~5.1kAutomated safety check: NotesMIT

Similar skills

  • Architecture Design Review

    bbartling/open-fdd

    A skill your agent uses to evaluate architecture, design proposals, refactors, module boundaries, dependency direction, data flow, concurrency model, and maintainability tradeoffs across any codebase.

    173 GitHub stars~1.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • Personal Assistant Review

    edonyzpc/personal-assistant

    Review uncommitted or PR diffs in the personal-assistant Obsidian plugin with project-specific risk lanes, second-layer future-risk checks, severity discipline, subagent review routing, and…

    147 GitHub stars~3.2k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Azsdk Common Pipeline Troubleshooting

    Azure/azure-sdk-for-android

    Official

    Diagnose and resolve failures in Azure SDK CI and generation pipelines.

    121 GitHub stars~496 tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed
  • LLM Council

    ffroliva/gflow-cli

    A skill your agent uses when a pr-council-review (PR or branch mode) result needs independent corroboration from a different model family before trusting a GREEN verdict — high-stakes…

    278 GitHub stars~2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Product Design

    qf-studio/navigator

    Automates design review, token extraction, component mapping, and implementation planning.

    355 GitHub stars~5.1k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check: notes
  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

More from jxnl/personal-monorepo-template

All 12 skills in this repo
  • Onboarding

    jxnl/personal-monorepo-template

    Start Assistant onboarding in a new or first-meeting Assistant chat.

    563 GitHub stars~877 tokensUpdated 3 mo ago
    Auto-check passed
  • Assistant

    jxnl/personal-monorepo-template

    Meet or work with Assistant, the user's relaxed ongoing work support.

    563 GitHub stars~635 tokensUpdated 3 mo ago
    Auto-check passed
  • Write Like Me Bootstrap

    jxnl/personal-monorepo-template

    Bootstrap a durable "write like me" skill from the user's own Slack and email writing.

    563 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • New Person

    jxnl/personal-monorepo-template

    Create or update a public-safe person note under people/ from the repository's people/person.md template.

    563 GitHub stars~250 tokensUpdated 3 mo ago
    Auto-check passed
  • New Project

    jxnl/personal-monorepo-template

    Bootstrap a new project or experiment directory with README and optional AGENTS.md files.

    563 GitHub stars~280 tokensUpdated 3 mo ago
    Auto-check passed
  • Audit AI Code

    jxnl/personal-monorepo-template

    Audit, de-slop, parameterize, modularize, or safely clean up AI-generated or AI-shaped backend/general code.

    563 GitHub stars~1.7k tokensUpdated 3 mo ago
    Auto-check passed

Questions about Ultragoal

What does Ultragoal do?

Design, critique, set, create, activate, or run durable Codex goals for persistent or long-running objectives. Ultragoal is an agent skill from jxnl/personal-monorepo-template. Design, critique, set, create, activate, or run durable Codex goals for persistent or long-running objectives.

When should I use Ultragoal?

Ultragoal fits situations like: the user says set a goal; activate goal mode; persistent goal; long-running objective.

How do I install Ultragoal in Claude Code?

Run `npx skills add jxnl/personal-monorepo-template --skill ultragoal -a claude-code`. Or copy the skill folder (.codex/skills/ultragoal in jxnl/personal-monorepo-template) into .claude/skills/ultragoal in your project. Claude Code loads it when a task matches its description.

How do I install Ultragoal in Codex?

Run `npx skills add jxnl/personal-monorepo-template --skill ultragoal -a codex`. Or copy the skill folder (.codex/skills/ultragoal in jxnl/personal-monorepo-template) into .agents/skills/ultragoal in your project. Codex loads it when a task matches its description.

Can I use Ultragoal in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jxnl/personal-monorepo-template --skill ultragoal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ultragoal, .gemini/skills/ultragoal, .github/skills/ultragoal and .opencode/skills/ultragoal in your project.

What does Ultragoal need to run?

SKILL.md names no scripts, command-line tools or credentials: Ultragoal is instructions for the agent only.

Does Ultragoal access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ultragoal safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ultragoal use?

No licence was found for Ultragoal or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Ultragoal use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ultragoal?

Skills that share tags, products or a category with Ultragoal: Architecture Design Review (bbartling/open-fdd, 173 stars), Personal Assistant Review (edonyzpc/personal-assistant, 147 stars), Azsdk Common Pipeline Troubleshooting (Azure/azure-sdk-for-android, 121 stars) and LLM Council (ffroliva/gflow-cli, 278 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ultragoal?

jxnl (a GitHub user) maintains it in jxnl/personal-monorepo-template, which has 563 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on June 22, 2026.

Source: jxnl/personal-monorepo-template on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.