Superloopy Evidence Loop
beefiker/superloopy
Runs a light task loop where each goal criterion passes only when a real evidence artifact exists, with progress stored in a `.superloopy` folder.
Runs a long task as a checkpointed goal loop: it creates goals, mirrors each step into a todo list, gathers evidence per criterion and lands every goal before the next.
Install ULW Loop
$ npx skills add code-yeongyu/oh-my-openagent --skill ulw-loop -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install code-yeongyu/oh-my-openagent ulw-loop --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/omo-senpi/skills/ulw-loop .claude/skills/ulw-loop && rm -rf skills-srcUse ~/.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/
Install the "ulw-loop" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/omo-senpi/skills/ulw-loop into .claude/skills/ulw-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ulw-loop", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/omo-senpi/skills/ulw-loopType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add code-yeongyu/oh-my-openagent --skill ulw-loop -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install code-yeongyu/oh-my-openagent ulw-loop --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/omo-senpi/skills/ulw-loop .agents/skills/ulw-loop && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ulw-loop" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/omo-senpi/skills/ulw-loop into .agents/skills/ulw-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ulw-loop", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add code-yeongyu/oh-my-openagent --skill ulw-loop -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install code-yeongyu/oh-my-openagent ulw-loop --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/omo-senpi/skills/ulw-loop .cursor/skills/ulw-loop && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ulw-loop" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/omo-senpi/skills/ulw-loop into .cursor/skills/ulw-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ulw-loop", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/code-yeongyu/oh-my-openagent.git --path packages/omo-senpi/skills/ulw-loop--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add code-yeongyu/oh-my-openagent --skill ulw-loop -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install code-yeongyu/oh-my-openagent ulw-loop --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/omo-senpi/skills/ulw-loop .gemini/skills/ulw-loop && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ulw-loop" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/omo-senpi/skills/ulw-loop into .gemini/skills/ulw-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ulw-loop", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install code-yeongyu/oh-my-openagent ulw-loopInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add code-yeongyu/oh-my-openagent --skill ulw-loop -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/omo-senpi/skills/ulw-loop .github/skills/ulw-loop && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ulw-loop" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/omo-senpi/skills/ulw-loop into .github/skills/ulw-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ulw-loop", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add code-yeongyu/oh-my-openagent --skill ulw-loop -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install code-yeongyu/oh-my-openagent ulw-loop --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/code-yeongyu/oh-my-openagent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/omo-senpi/skills/ulw-loop .opencode/skills/ulw-loop && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ulw-loop" agent skill from https://github.com/code-yeongyu/oh-my-openagent/tree/dev/packages/omo-senpi/skills/ulw-loop into .opencode/skills/ulw-loop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ulw-loop", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ulw-loop- GitHub stars
- 70k
- Token cost
- ~3.2k tokens
- SKILL.md length
- 1,682 words
- Files
- 3 (incl. references)
- Skills in repo
- 44
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Runs a long task as a checkpointed goal loop: it creates goals, mirrors each step into a todo list, gathers evidence per criterion and lands every goal before the next.
- Works in 5 steps: Create goals from a JS eval cell:… → Register the aggregate objective from… → Mirror every atomic step into the live… → …
- Long-running delivery that needs durable, checkpointed progress
- SKILL.md covers Run contract, The SDK: one import, then…, Non-Negotiables and Team mode: decide it, do not…, plus 2 more sections
- Calls git
What it does
This skill is a short run contract for durable, evidence-led delivery. Goals are created from a JavaScript eval cell through an agent toolkit SDK that the host extension publishes, then the aggregate objective is registered with `create_goal` and every atomic step is mirrored into a live todo checklist with exactly one step in progress at a time.
Each goal is treated as a phase. It gets its own worktree off the integration base, its dependency-ordered lanes run as a single workflow, and every criterion is checked against real-surface evidence, since passing tests alone do not count as done. When a goal completes, a checkpoint call records the evidence and the worktree is landed on the integration base. The loop stops once the stated stop condition holds. Two reference files hold the full workflow and the goal-definition guidance.
When your agent uses it
- Long-running delivery that needs durable, checkpointed progress
- A request for a goal loop or ulw-loop by name
- Work where each phase must be proven with evidence such as manual QA, not only tests
- Splitting a large change into goals that each land from their own worktree
Example prompts
- “Use ulw-loop to rebuild the export feature, creating goals first and recording evidence for each one.”
- “Run a goal loop for the database migration, with a checkpoint after every phase.”
- “I want durable, checkpointed execution for the new onboarding flow, including manual QA evidence.”
Requirements
- The agent toolkit SDK published by the host extension at OMO_AGENT_TOOLKIT_SDK_ROOT
- A git repository with an integration base branch for per-goal worktrees
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Create goals from a JS eval cell: agentToolkit.createGoals({ brief }) after the SDK import below. The SDK binds this session from the host…
- Register the aggregate objective from the returned handoff with create_goal, shaped by references/define-goal.md. Goal creation is NEVER…
- Mirror every atomic step into the live todo checklist: one granular step per action, exactly one in_progress, transitions marked the…
- Treat each goal as a phase: create its own worktree off the integration base; dispatch its dependency-ordered lanes as ONE workflow run…
- Stop when the goal's WHEN-TO-STOP line holds with evidence in hand.
What it can do on your machine
Read from SKILL.md and the folder at commit cbd7dd2. 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
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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
ULW Loop loads about 3.2k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 42 tokens; SKILL.md has 1,682 words of instructions outside code blocks.
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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,682 words (~3,155 tokens).
“Use this skill when the user asks for ulw-loop, ulw, durable goal execution, evidence-led work, manual QA, or checkpointed long-running delivery.”
- name
- ulw-loop
- argument-hint
- <goal>
- metadata.short-description
- Goal-like ultrawork loop for systematic decomposition
Files
SKILL.md and 2 other files (references) in packages/omo-senpi/skills/ulw-loop of code-yeongyu/oh-my-openagent.
- SKILL.md
- references/define-goal.md
- references/full-workflow.md
Open the folder on GitHubat commit cbd7dd2
Used in 1 other repository
We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in code-yeongyu/oh-my-openagent, which our catalogue first saw on October 7, 2026.
Compare with similar skills
ULW Loop 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| ULW Loop this skillcode-yeongyu/oh-my-openagent | 70k | — | ~3.2k | Automated safety check: Pass | Custom licence | |
| Superloopy Evidence Loopbeefiker/superloopy | 111 | 1 repos | ~5.9k | Automated safety check: Pass | MIT | |
| Show Me Your Work Decision Logcursor/plugins | 10k | 9 repos | ~1.6k | Automated safety check: Pass | None | |
| Incremental Implementationaddyosmani/agent-skills | 102k | 1 repos | ~2.3k | Automated safety check: Pass | MIT | |
| PUA Looptanweai/pua | 20k | — | ~1.1k | Automated safety check: Pass | MIT | |
| agtx One-Shot Project Runnerfynnfluegge/agtx | 1.7k | — | ~3.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Show Me Your Work Decision Log
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
Incremental Implementation
addyosmani/agent-skills
Delivers a change in thin vertical slices, each implemented, tested, verified and committed before the next, using vertical, contract-first or risk-first slicing.
PUA Loop
tanweai/pua
Runs an unattended iterate-until-verified loop in which a user-set verify command, not the agent's own claim, decides when the task is finished.
agtx One-Shot Project Runner
fynnfluegge/agtx
Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.
Agtx Task Sweep
fynnfluegge/agtx
Breaks a conversation's results into feature-level tasks and pushes them to the agtx kanban board, where each task gets its own worktree and agent session.
More from code-yeongyu/oh-my-openagent
All 44 skills in this repoast-grep Structural Search
code-yeongyu/oh-my-openagent
Searches and rewrites code by syntax-tree shape across 25 languages with ast-grep, for codemods, structural queries and YAML lint rules, using a Python wrapper script.
Browser Control with Omowright
code-yeongyu/oh-my-openagent
Drives a real browser through the omowright library, either the user's own signed-in browser or a separate browser the code launches, for forms, QA, screenshots and scraping.
Codex Plugin QA
code-yeongyu/oh-my-openagent
Tests the omo Codex plugin in an isolated CODEX_HOME with a local mock model, proving hooks fired through app-server notifications without touching ~/.codex.
Coding Agent Session Finder
code-yeongyu/oh-my-openagent
Finds, reads and reconstructs past coding-agent sessions across Codex, Claude, OpenCode, Senpi and many other local agent logs.
LSP Setup
code-yeongyu/oh-my-openagent
Detects which languages a project uses, installs the matching language server, writes its config and checks it with a real call so diagnostics and go-to-definition work.
OpenCode QA Toolkit
code-yeongyu/oh-my-openagent
Tests the opencode coding agent itself: its CLI, server, plugin hooks and events, the terminal UI under tmux, and its SQLite session database, using tested helper scripts.
Related
Categories
Questions about ULW Loop
What does ULW Loop do?
Runs a long task as a checkpointed goal loop: it creates goals, mirrors each step into a todo list, gathers evidence per criterion and lands every goal before the next. This skill is a short run contract for durable, evidence-led delivery. Goals are created from a JavaScript eval cell through an agent toolkit SDK that the host extension publishes, then the aggregate objective is registered with `create_goal` and every atomic step is mirrored into a live todo checklist with exactly one step in progress at a time.
When should I use ULW Loop?
ULW Loop fits situations like: long-running delivery that needs durable, checkpointed progress; A request for a goal loop or ulw-loop by name; work where each phase must be proven with evidence such as manual QA, not only tests; splitting a large change into goals that each land from their own worktree.
How do I install ULW Loop in Claude Code?
Run `npx skills add code-yeongyu/oh-my-openagent --skill ulw-loop -a claude-code`. Or copy the skill folder (packages/omo-senpi/skills/ulw-loop in code-yeongyu/oh-my-openagent) into .claude/skills/ulw-loop in your project. Claude Code loads it when a task matches its description.
How do I install ULW Loop in Codex?
Run `npx skills add code-yeongyu/oh-my-openagent --skill ulw-loop -a codex`. Or copy the skill folder (packages/omo-senpi/skills/ulw-loop in code-yeongyu/oh-my-openagent) into .agents/skills/ulw-loop in your project. Codex loads it when a task matches its description.
Can I use ULW Loop 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 code-yeongyu/oh-my-openagent --skill ulw-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ulw-loop, .gemini/skills/ulw-loop, .github/skills/ulw-loop and .opencode/skills/ulw-loop in your project.
What does ULW Loop need to run?
Going by SKILL.md and its folder, ULW Loop needs the command-line tools its instructions call (git). Our summary lists: The agent toolkit SDK published by the host extension at OMO_AGENT_TOOLKIT_SDK_ROOT; A git repository with an integration base branch for per-goal worktrees.
Does ULW Loop access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is ULW Loop 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 ULW Loop use?
ULW Loop has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does ULW Loop use?
About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 10k tokens, read only when the agent opens those files.
What are the alternatives to ULW Loop?
Skills that share tags, products or a category with ULW Loop: Superloopy Evidence Loop (beefiker/superloopy, 111 stars), Show Me Your Work Decision Log (cursor/plugins, 10k stars), Incremental Implementation (addyosmani/agent-skills, 102k stars) and PUA Loop (tanweai/pua, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains ULW Loop?
code-yeongyu (a GitHub user) maintains it in code-yeongyu/oh-my-openagent, which has 69,850 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on October 7, 2026.
Source: code-yeongyu/oh-my-openagent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.