ulw-loop

ulw-loop is a skill for Claude Code, Codex from code-yeongyu/lazyclaudecode. It costs 24 tokens per session (3,589 once invoked), scanned C, original, MIT.

A goal-management workflow for breaking large tasks into smaller steps and carrying them through multiple sessions. It requires proof from actual use, not just passing tests.

In plain words
What is it for?
Use it to manage several goals, choose real-world checks such as HTTP requests or browser sessions, and record the evidence in project files.
Why use it?
It helps prevent work from being marked complete without evidence that the result works in practice. It also keeps a record of decisions, progress, failures, and checkpoints.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Codex; $skill-name invocation.

Part of the omo plugin — 14 skills, 6 agents, 1 hook, 2 MCP servers shipped together

Good fit Use it to manage several goals, choose real-world checks such as HTTP requests or browser sessions, and record the evidence in project files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/code-yeongyu/lazyclaudecode/ultragoal
Install

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.

Any agent
npx skills add code-yeongyu/lazyclaudecode --skill ultragoal
Clone the repo
git clone --depth 1 https://github.com/code-yeongyu/lazyclaudecode

Made for: Claude Code, Codex.

Or install omo, the plugin that ships this one along with the rest of its 14 skills, 6 agents, 1 hook, 2 MCP servers.

Wrote 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.

agentmods badge for ulw-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/code-yeongyu/lazyclaudecode/ultragoal/github.svg)](https://agentmods.dev/skills/code-yeongyu/lazyclaudecode/ultragoal)
Your own site
<a href="https://agentmods.dev/skills/code-yeongyu/lazyclaudecode/ultragoal"><img src="https://agentmods.dev/badge/skills/code-yeongyu/lazyclaudecode/ultragoal/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.

agentmods 80×15 button for ulw-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/code-yeongyu/lazyclaudecode/ultragoal"><img src="https://agentmods.dev/badge/skills/code-yeongyu/lazyclaudecode/ultragoal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,589 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.03589
Opus 5 $0.00012 $0.01795
Sonnet 5 $0.00005 $0.00718
Haiku 4.5 $0.00002 $0.00359

Measured 9d ago against content hash d267094bf626, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

ulw-loop scanned grade C with 2 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 9d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

5. CLEAN (PAIRED, NEVER SKIP): tear down every runtime artifact step 3 spawned BEFORE recording — server PIDs (`kill`, verify `kill -0` fails), `tmux` sessions (`tmux kill-session -t ulw-qa-<criterion>`; confirm `tmux ls

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **HTTP call** — hit the live endpoint with `curl -i` (or a Playwright APIRequestContext); capture status line + headers + body.
plugins/omo/components/ultragoal/skills/ultragoal/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Expert goal orchestration agent. Plan multi-goal work that survives across turns and sessions. Use GPT-5.x style: outcome-first, evidence-bound, atomic decisions, no nested branching prose.

Goal

Deliver every goal in .omo/ultragoal/goals.json end-to-end. Prove EVERY success criterion with captured observable evidence from a real-usage scenario you actually ran (HTTP call / tmux / browser use / computer use — see the Manual-QA channels below). TESTS ALONE NEVER PROVE DONE. A green test suite is supporting evidence, not completion proof. Audit each pass, fail, block, steering change, and checkpoint in .omo/ultragoal/ledger.jsonl.

Manual-QA channels (PICK ONE PER CRITERION — ACTUALLY RUN IT)

For every criterion, build a real-usage scenario through ONE of these four channels and run it yourself before recording PASS. The full test suite being green is NEVER verification on its own.

  1. HTTP call — hit the live endpoint with curl -i (or a Playwright APIRequestContext); capture status line + headers + body.
  2. tmuxtmux new-session -d -s ulw-qa-<criterion>, drive with send-keys, dump via tmux capture-pane -pS -E -; transcript is the artifact.
  3. Browser use — drive the real page via Playwright / puppeteer / Chromium; capture action log + screenshot path.
  4. Computer use — OS-level GUI automation (computer-use agent, AppleScript, xdotool, etc.) against the running app; capture action log + screenshot.

Auxiliary surfaces (pure CLI stdout / DB state diff / parsed config dump) satisfy CLI- or data-shaped criteria but NEVER replace a channel scenario for user-facing behavior. --dry-run, printing the command, "should respond", and "looks correct" never count.

Artifacts

  • .omo/ultragoal/brief.md: original brief and durable constraints.
  • .omo/ultragoal/goals.json: goals with embedded successCriteria per goal.
  • .omo/ultragoal/ledger.jsonl: append-only audit trail.
  • Read artifacts before resuming, steering, or checkpointing.
  • Never invent state outside .omo/ultragoal artifacts or omo ultragoal status --json.

Read the full file on GitHub · 199 lines

Files

What ships with it

2 files 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.

Changes

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.

  1. 9d ago First seen · 199 lines · 24 tokens per session scan C d267094bf626

Subscribe to this mod's changes

ulw-loop is a skill published in the GitHub repository code-yeongyu/lazyclaudecode (18 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 3,589 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

setup

A project-initialization workflow for creating a new Workframe project or connecting an existing project to Workframe.

ryanzhao1011/workframe · 88 tokens

dont-leave-me

A stop-before-finishing checklist for an agent that checks whether requested work, changed files, verification, and cleanup have actually been handled.

Keonho-Chu/menhera-loop · 31 tokens

feature-breakdown

A guide for breaking a large request into an epic, user stories, and smaller tasks. An epic is a broad goal, a user story describes one independently useful outcome, and a task is a concrete piece of work.

ryanzhao1011/workframe · 41 tokens

task-management

A project task-management system built around a board.yaml file, a text file that records tasks, statuses, priorities, owners, dates, dependencies, and progress totals.

ryanzhao1011/workframe · 20 tokens

workflow

The operating pipeline for all development work — 6 phases (Brief, Plan, Build, Verify, Ship, Learn) with risk tiers that decide how much process a task gets. Use at the start of any development task to pick the tier and execution mode, when unsure whether a task needs a plan/tests/review, or when another skill needs…

AbdurRafay2004/handoff · 87 tokens

traction-eos

Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…

wondelai/skills · 147 tokens