ulw-loop SKILL.md skillA
ulw-loop from code-yeongyu/oh-my-openagent is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add code-yeongyu/oh-my-openagent/ulw-loop@git:20261106.e313b72Pins git:20261106.e313b72 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- code-yeongyu/oh-my-openagent
- Path
packages/omo-senpi/skills/ulw-loop/SKILL.md- Versions recorded
- 16
- Latest version
- git:20261106.e313b72, committed Nov 6, 2026
- First version recorded
- Sep 3, 2026
- Size
- 13,144 bytes
- Repository stars
- 70,763
- License
- a license file GitHub does not identify
A goal-like loop that decomposes work into systematic, evidence-bound ultrawork steps. Use when the user wants a goal loop or durable, checkpointed execution.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# ulw-loop
Use this skill when the user asks for `ulw-loop`, `ulw`, durable goal execution, evidence-led work, manual QA, or checkpointed long-running delivery.
This skill is compact by design: the run contract below is the whole bootstrap. `references/full-workflow.md` and `references/define-goal.md` carry the full doctrine; open a section only when the phase you are in needs it.
## Run contract
1. Create goals from a JS eval cell: `agentToolkit.createGoals({ brief })` after the SDK import below. The SDK binds this session from the host env, so never pass a session id or a plan path. If the envelope reports `ULW_LOOP_PLAN_EXISTS_COMPLETE` (this session's aggregate is already complete), unrelated new work needs a fresh session; `createGoals({ brief, force: true })` is only for deliberately overwriting completed evidence.
2. Register the aggregate objective from the returned handoff with `create_goal`, shaped by `references/define-goal.md`. Goal creation is NEVER skipped.
…Read the whole file at its exact version.
How to install
mdr add code-yeongyu/oh-my-openagent/ulw-loop@sha256:5efaafb4a3506ab9The line at the top of this page pins the label git:20261106.e313b72, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_jaqe4rjbjjr5532h)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 16 versions of this file, between Sep 3, 2026 and Nov 6, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261106.e313b72 latest | 2026-11-06 | e313b72 | 13,144 B | A | view · diff |
| git:20261105.f78e95c | 2026-11-05 | f78e95c | 12,865 B | A | view · diff |
| git:20261013.49da377 | 2026-10-13 | 49da377 | 12,836 B | A | view · diff |
| git:20261012.c76ac26 | 2026-10-12 | c76ac26 | 12,832 B | A | view · diff |
| git:20261011.584b00a | 2026-10-11 | 584b00a | 13,097 B | A | view · diff |
| git:20260929.9a41ccb | 2026-09-29 | 9a41ccb | 12,630 B | A | view · diff |
| git:20260916.a70ebbf | 2026-09-16 | a70ebbf | 12,606 B | A | view · diff |
| git:20260916.43772b2 | 2026-09-16 | 43772b2 | 11,670 B | A | view · diff |
| git:20260916.585bfa1 | 2026-09-16 | 585bfa1 | 10,949 B | A | view · diff |
| git:20260915.cf3fe65 | 2026-09-15 | cf3fe65 | 10,661 B | A | view · diff |
| git:20260912.8da9cbd | 2026-09-12 | 8da9cbd | 8,566 B | A | view · diff |
| git:20260907.d4345c5 | 2026-09-07 | d4345c5 | 7,888 B | A | view · diff |
| git:20260904.2790172 | 2026-09-04 | 2790172 | 7,424 B | A | view · diff |
| git:20260903.130afdf | 2026-09-03 | 130afdf | 8,298 B | A | view · diff |
| git:20260903.286a6dc | 2026-09-03 | 286a6dc | 7,450 B | A | view · diff |
| git:20260903.91248d2 | 2026-09-03 | 91248d2 | 7,360 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13144 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
code-yeongyu/oh-my-openagent · 70,763 stars · license a license file GitHub does not identify · pushed 2026-11-07 · branch dev
API
GET https://markdownregistry.com/api/v1/artifacts/art_jaqe4rjbjjr5532h GET https://markdownregistry.com/api/v1/resolve?ref=code-yeongyu/oh-my-openagent/ulw-loop GET https://markdownregistry.com/api/v1/blob/5efaafb4a3506ab986701ac6f80302fbb08f1207d8958faaead1a7ca308e587d
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from code-yeongyu/oh-my-openagent
Every file in code-yeongyu/oh-my-openagent