Run any Skill in Manus with one click

ulw-status

Stars3

Forks0

UpdatedJuly 15, 2026 at 03:55

Show the current ULW session state — workflow mode, domain, intent, counters, and flags. Use for debugging or inspecting what the hooks decided. Pass `summary` for a compact end-of-session recap, `classifier` for intent-classifier telemetry, or `explain` for a per-flag rationale.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

X0x888

X0x888/oh-my-claude

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	ulw-status
description	Show the current ULW session state — workflow mode, domain, intent, counters, and flags. Use for debugging or inspecting what the hooks decided. Pass `summary` for a compact end-of-session recap, `classifier` for intent-classifier telemetry, or `explain` for a per-flag rationale.

ULW Status

Parse any argument passed with the skill invocation (stored in $ARGUMENTS). Treat the arguments case-insensitively.

If the user passed summary, -s, or --summary, run the compact recap:

bash ~/.claude/skills/autowork/scripts/show-status.sh --summary

If the user passed classifier, -c, or --classifier, run the intent-classifier telemetry surface:
```
bash ~/.claude/skills/autowork/scripts/show-status.sh --classifier
```
If the user passed explain, -e, or --explain, run the per-flag rationale (v1.30.0):
```
bash ~/.claude/skills/autowork/scripts/show-status.sh --explain
```

Otherwise, run the full diagnostic status:

bash ~/.claude/skills/autowork/scripts/show-status.sh

Display the output as-is.

The --summary form is the right choice at end-of-session — it folds session duration, token/cache totals, top positive-fresh-token role/model drivers, edit counts, guard blocks, classifier misfires, reviewer verdicts, and commits made during the session onto a compact view. It surfaces "invisible friction" signals that the full dump buries, so the user can see patterns (e.g. "3 sessions in a row with mostly-misfire PreTool blocks → tune the classifier") that would otherwise live only in memory.

The --explain form (v1.30.0) walks the active oh-my-claude.conf and prints each flag's current value, default, and one-line purpose, grouped by category. Non-default values are flagged with a * marker. Use this when you want to disable a flag (e.g., intent_broadening, prompt_persist) but need to know what it does first — closes the "what does each flag actually do?" gap that previously required reading the 422-line oh-my-claude.conf.example file.

If the session shows issues (guard exhausted, high stall counter, missing verification, many classifier misfires), briefly note what it means.

More from this repository

same repository

autowork

X0x888/oh-my-claude

Maximum-autonomy professional work mode. Use for non-trivial coding, writing, research, planning, or mixed tasks that should be carried through the right specialist workflow with minimal hand-holding.

2026-07-163

ulw-off

X0x888/oh-my-claude

Deactivate ultrawork mode for the addressed session. Clears its workflow and enforcement state without affecting concurrent Claude sessions.

2026-07-153

council

X0x888/oh-my-claude

Adaptive project evaluation that maps the task's actual risks, assembles the smallest useful specialist team, and fills material coverage gaps before synthesis.

2026-07-153

omc-config

X0x888/oh-my-claude

Guided oh-my-claude configuration via multi-choice prompts — first-time setup walkthrough, post-update review, or ad-hoc inspect/change. Auto-detects mode from `~/.claude/oh-my-claude.conf`. Use when the user asks to install, set up, configure, update, walk through settings, change flags, turn the watchdog or bias-defense on/off, switch model tier, or any phrase like "help me install/update/configure oh-my-claude", "show my settings", "what flags do I have on".

2026-07-153

skills

X0x888/oh-my-claude

List all available oh-my-claude skills with descriptions and when to use each one.

2026-07-153

test-audit

X0x888/oh-my-claude

Audit whether a project's tests still earn their runtime and maintenance cost. Maps behavior contracts to owners, identifies redundant or obsolete proof, and recommends KEEP, EXTEND, MERGE, REPLACE, DELETE, or ADD with evidence. Use --apply to implement proven portfolio changes.

2026-07-153

name	ulw-status
description	Show the current ULW session state — workflow mode, domain, intent, counters, and flags. Use for debugging or inspecting what the hooks decided. Pass `summary` for a compact end-of-session recap, `classifier` for intent-classifier telemetry, or `explain` for a per-flag rationale.

ULW Status

Parse any argument passed with the skill invocation (stored in $ARGUMENTS). Treat the arguments case-insensitively.

If the user passed summary, -s, or --summary, run the compact recap:

bash ~/.claude/skills/autowork/scripts/show-status.sh --summary

If the user passed classifier, -c, or --classifier, run the intent-classifier telemetry surface:
```
bash ~/.claude/skills/autowork/scripts/show-status.sh --classifier
```
If the user passed explain, -e, or --explain, run the per-flag rationale (v1.30.0):
```
bash ~/.claude/skills/autowork/scripts/show-status.sh --explain
```

Otherwise, run the full diagnostic status:

bash ~/.claude/skills/autowork/scripts/show-status.sh

Display the output as-is.

If the session shows issues (guard exhausted, high stall counter, missing verification, many classifier misfires), briefly note what it means.