loop
/loop
Work through the taskboard unattended for hours, pacing against the usage limits and filling the gap before a reset with CPU-only jobs. Use when asked to run all day, work unattended, or loop over tickets.
- Author
- tjqscott ↗
- Repository
- dory ↗
- Licence
- MIT
- Last repository change
- 05.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 05.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Work through the taskboard unattended for hours, pacing against the usage limits and filling the gap before a reset with CPU-only jobs. Use when asked to run all day, work unattended, or loop over tickets.
Original author description
Work through the taskboard unattended for hours, pacing against the usage limits and filling the gap before a reset with CPU-only jobs. Use when asked to run all day, work unattended, or loop over tickets.
How it works
SKILL.md has no level-two headings · 15 lines, 189 words
SKILL.md preview
--- name: loop description: Work through the taskboard unattended for hours, pacing against the usage limits and filling the gap before a reset with CPU-only jobs. Use when asked to run all day, work unattended, or loop over tickets. --- # Loop Follow AGENTS.md VI. Every prompt carries a `[dory]` line with the time and the five-hour usage. 1. **Pick** the top item under `## Now` in `wiki/tickets.md`, or else `## Next`. State its check before starting. 2. **Work it.** When its check passes, run the learn skill on what it taught and move it to `## Done`. 3. **Before each new item, read the `[dory]` line:** - **Below 90%:** continue. - **90% or more:** start no model-heavy item. Finish the current one, and queue jobs that need no model under `## CPU`, each with its command and output path. - **95% or more:** launch every `## CPU` job in the background with its output going to a file, run the handoff skill, and start nothing else. - **At 100%**, Claude Code pauses and resumes after the reset (wait and continue, v2.1.234+). On resume, read the handoff first, collect the CPU outputs, and carry on from step 1. 4. **If usage is unknown** (no statusline data), say so once and pace by the clock instead. 5. **Never** push, merge or delete unless the project's own instructions already allow it.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · tjqscott/dory | 86 | MIT |
| mickeyyaya/evolve-loop | 100 | Apache-2.0 |
| relai-ai/agent-eval-loop | 100 | Apache-2.0 |
| SethGammon/Citadel | 100 | MIT |
| alirezarezvani/claude-skills | 100 | MIT |
| x-cmd/x-cmd | 100 | Apache-2.0 |
| in-the-loop-labs/pair-review | 100 | Apache-2.0 |
| railly/skills | 100 | MIT |
| slogsdon/loop-and-gate-foundation | 100 | MIT |
Database snapshot: 13.11.2026 · package version 22a4c40d1c46 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100burn-jira
Work labelled Jira tickets unattended with idle Claude Code subscription quota — set up, preview, schedule, and report on a `burn process jira` run. Use when the user says "work my Jira tickets while I'm out", "auto pick labelled tickets", "burn my backlog", "run this over the… - 100unattended-runs
Use when work must run unattended for hours or days, survive usage limits or a closed session ("keep going while I'm away", "this will cross my usage limit", "run this overnight / over the weekend"), or to set up a heartbeat, resume an interrupted run or audit one. Not for a… - 100loop-designer
Compile a goal into a durable, file-backed agent loop — a .loop/<name>/ charter any coding agent (Claude Code, Codex, Gemini, Grok) can execute unattended. Use when the user wants to "build a loop", "design a loop", "run X continuously/24-7", "make an agent keep working on Y",… - 95work-loop
Use for unattended progression of plan tasks, HANDOFF items, tech debt, or roadmaps. Not for one-time handoff or user decisions. - 100spec-loop
Run an approved Spec-backed Plan (design.md and plan.json both present) unattended to a draft PR: implement and review each batch with fresh subagents, commit, then finish with one whole-branch review. Use when the user says "run it to the end" or "implement everything and open a PR". - 95shift
This skill should be used when the user asks to "work a shift", "run unattended", "keep working while I'm away", "guild shift", "take the night shift", "work the board while I'm out", "run autonomously", "keep going without me", "work overnight", "run until you need me", or any…