Binding ultrawork mode directive for omo-senpi. When a prompt contains ultrawork or ulw, the omo input hook injects the full directive as a hidden custom message (customType omo-ultrawork:directive, display false) ahead of the user's text, which is left untouched; a prompt queued while the agent is streaming instead carries the directive appended inside that same message. The directive is present in the conversation context; on the idle path it is not shown in the visible prompt, while a queued prompt carries the directive visibly (exactly as before this change). When the directive is already present in the conversation, do not read this file again - this file is that same directive. Read this file only when ultrawork mode is requested and the directive is not already present in the conversation.
ulw-loop
ulw-loop is an open-source workflow skill for Claude Code and compatible agents, published by code-yeongyu. Its author describes it as: “Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.”. The project has 68k stars on GitHub and ships custom license terms, so review them before reuse. Add it to your setup with `git clone https://github.com/code-yeongyu/oh-my-openagent ~/.claude/skills/ulw-loop`.
What ulw-loop does
Use this skill when the user asks for `ulw-loop`, `ulw`, durable goal execution, evidence-led work, manual QA, or checkpointed long-running delivery.
Installation
Add ulw-loop to your agent with:
git clone https://github.com/code-yeongyu/oh-my-openagent ~/.claude/skills/ulw-loopAlways review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.
What's inside
The SKILL.md for ulw-loop is organised into these sections:
- Required First Steps
- Non-Negotiables
- Team mode: decide it, do not default to it
- Native Senpi Task Contract
When to use it
Reach for ulw-loop when you want workflow help from your agent without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.
Strengths
- Ships in code-yeongyu/oh-my-openagent, an established project with 67,982 GitHub stars
- Actively maintained (recent commits)
Things to check
- No license declared — confirm terms with the author before reuse
Topics
Frequently asked questions
- What does ulw-loop do?
- Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.
- How do I install ulw-loop?
- Run git clone https://github.com/code-yeongyu/oh-my-openagent ~/.claude/skills/ulw-loop in your agent, then reload your skills. Review the source at https://github.com/code-yeongyu/oh-my-openagent before installing.
- Is ulw-loop free to use?
- ulw-loop is publicly available on GitHub, but code-yeongyu has not declared a standard open-source license (Other). Confirm the terms with the author before reusing it.
- Where does ulw-loop come from?
- ulw-loop ships inside code-yeongyu/oh-my-openagent, a repository that contains 46 catalogued skills in total. The repository's 67,982 GitHub stars apply to that whole collection, not to this skill on its own.
Related skills
More Workflow →Team-first maximum-saturation research orchestration for omo-senpi. Scopes solo, ALWAYS asks which final format to render (PDF+DOCX default), then stands up a max-size cooperating team (team_create): one member per axis plus skeptic/red-team members for ultradebate/hyperdebate cross-critique, explore/librarian lanes, live ulw-loop journaling, an EXPAND loop until leads run dry, claims proven by code or the claim-graph gate, and a cited synthesis with charts/Mermaid/assets behind visual-QA and `writing` proofread gates. ACTIVATES ONLY on an explicit user demand for research: the word 'ulw-research' ('/ulw-research', '$ulw-research'), any 'ulw' research wording, 'ultradebate' or 'hyperdebate' research requests, or an explicit request for research / deep research / an ultra-precise investigation, in any language. Never self-activates for ordinary questions, debugging, or implementation context-gathering. While active it overrides exploration-bounding defaults: exhaustive coverage is the goal.
Persistent Codex-style goal tracking for pi. Use when the user explicitly asks to set, continue, audit, pause, resume, complete, or inspect a long-running goal.
MUST USE when asked to find, read, list, search, inspect, fetch, export, or reconstruct coding-agent sessions across Codex, Claude Code/Desktop, OpenCode, OMO/Senpi/pi, oh-my-pi (omp), gajae-code (gjc), OpenClaw, Factory Droid, Amp, Gemini/Kimi/Qwen CLIs, Codebuff, Roo/Kilo/Cline, Kodu, Cursor CLI, Aider, Aside browser-agent sessions, or unknown local agent logs. Covers transcripts, session IDs, rollout JSONL, state SQLite, Claude projects/pre-compact histories, OpenCode messages/parts, child/subagent linkage, cwd/model/time/token filters, archives, and cost clues. Expands fuzzy recall into parallel query lanes and first probes known stores so absent platforms are skipped cheaply. Triggers: coding agent sessions, Codex/Claude/OpenCode/OMO/Senpi/pi/oh-my-pi/omp/gajae-code/gjc/OpenClaw/Droid/Amp/Kodu/Cursor/Aider/Aside sessions, transcript search, session history, session ID, read transcript, token usage, subagent sessions, what did I do yesterday, did we already do this.
MUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong responses, stuck processes, memory leaks, async misbehavior, unexplained timing, reverse engineering. Runs a hypothesis-driven loop: form ≥3 hypotheses, investigate in parallel, after 2 failed rounds spawn Oracles from orthogonal angles, confirm root cause, lock with a failing test, fix minimally, QA by actually USING the system, scrub artifacts. The actual HOW lives in `references/` — READ THEM. Triggers: 'debug this', 'why is X not working', 'hanging', 'attach a debugger', 'reverse engineer', 'pwndbg', 'gdb', 'lldb', 'node inspect', 'pdb', 'dlv', 'delve', 'rust-gdb', 'set a breakpoint', 'context window exploded', 'why is the response empty', 'why is this happening', 'trace this bug', 'reproduce and fix', 'silent failure', 'HTTP 200 but empty', 'why did it stop', 'inspect the binary', 'playwright', 'flaky test', 'fails intermittently', 'passes in isolation', 'only fails in CI'.