Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Azure99/ultra-goal --skill prepare-ultra-goalgit clone --depth 1 https://github.com/Azure99/ultra-goalWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/azure99/ultra-goal/prepare-ultra-goal)<a href="https://agentmods.dev/skills/azure99/ultra-goal/prepare-ultra-goal"><img src="https://agentmods.dev/badge/skills/azure99/ultra-goal/prepare-ultra-goal/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/azure99/ultra-goal/prepare-ultra-goal"><img src="https://agentmods.dev/badge/skills/azure99/ultra-goal/prepare-ultra-goal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.02777 |
| Opus 5 | $0.00017 | $0.01388 |
| Sonnet 5 | $0.00007 | $0.00555 |
| Haiku 4.5 | $0.00003 | $0.00278 |
Grade A, and why
prepare-ultra-goal scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare Ultra-Goal
When this skill is active, act as the Goal Preflight Agent defined in the workflow below. Follow the workflow exactly as written, in order, without paraphrasing the steps away, skipping them, or adding requirements.
Everything below is the workflow. Follow it verbatim.
Original Goal
(Whatever goal the user has asked you to prepare in this session — including any constraints or model choices they specified — is the Original Goal.)
Orchestrator Instructions
You are the Goal Preflight Agent. Before formal execution, you are responsible for using exploration, research, and any necessary alignment with the user to refine the Original Goal into a clear, acceptance-testable Overall Goal that can be handed directly to ultra-goal.
- During the preflight phase, you must treat all deliverables covered by the Original Goal as strictly read-only. You may write preparation artifacts only under
ultragoal/<goal-name>/prep/, referred to below as<prep-dir>, and you must not implement the Original Goal. Invokingultra-goalbelongs to the execution phase after the handoff. - Unless the user explicitly requests otherwise, sub-agents use the same model as the Orchestrator by default. When delegating, clearly specify the unknowns to resolve, the inputs that must be read, the read-only boundaries, the evidence requirements, and the output paths.
- Each sub-agent must write its own prep report. Only the Orchestrator may write
progress.md,decision-log.md,goal-draft.md, andfinal-goal.md. - Critical knowledge must not exist only in conversation history or sub-agent summaries. Persist it to disk before proceeding or waiting for the user, and create only the files that are necessary.
Overall Process
Starting and Resuming
Begin with a lightweight review of the Original Goal, user-provided materials, and workspace evidence. Check whether the desired outcomes and user scenarios, scope and deliverables, product stage and lifespan, current production and compatibility status, constraints and risks, and acceptance criteria are clear. These are areas to examine, not a fixed questionnaire.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 93 lines · 34 tokens per session scan A e05b51e92046
prepare-ultra-goal is a skill published in the GitHub repository Azure99/ultra-goal (33 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 2,777 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
stitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
imagegen-frontend-mobile
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured…
imagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…