agentleFS
thepictishbeastthepictishbeast/claude-tools/skills/loop/SKILL.md

loop

Skill1 starsChanged 6 months agoMITView on GitHub

Manage active Claude Code /loop cron jobs — pause, resume, stop/cancel, edit (interval/prompt), track an untracked cron into history, or update the claude-tools install. Use whenever the user wants to pause / resume / stop / cancel / kill / change / reschedule a loop, register an existing cron, or upgrade loop tooling. Pass the verb as the first argument (e.g. "pause", "resume 5m", "stop", "edit", "track <id>", "update").

55 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use review-bugbot, origin and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • 0mlkrizzz655335vSkill

    review-bugbot

    缺陷导向代码审查。用 Bugbot 子代理找 bug。

    Also in 4 projects that use this

  • 0mlkrizzz655335vSkill

    origin

    origin CLI 管理。安装、登录、更新、修复 origin.cursor.com 的 CLI。"disabled-environments:

    Also in 3 projects that use this

  • PandelisZSkill

    update-cli-config

    View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.

    Also in 4 projects that use this

  • 32103210Skill

    migrate-to-skills

    Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.

    Also in 4 projects that use this

  • 32103210Skill

    update-cursor-settings

    Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.

    Also in 4 projects that use this

  • MicrosoftSkill

    automate

    Propose an automation from a completed task or a new idea, then create it after approval. Use when the user asks to create an automation or wants scheduled local or cloud agent work.

    Also in 4 projects that use this

  • +3 more from 0mlkrizzz655335v
  • +1 more from 32103210

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Don't CronDelete + CronCreate from scratch for an edit — that loses the full prompt unless you pulled it first.

    line 33
  2. Very specific:

    Don't append a history event if the Cron* call failed.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 50 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/loop — manage Claude Code loop cron jobs (Rust-binary backed)

One skill for the whole loop-management family (consolidated from the former loop-pause / loop-resume / loop-stop / loop-edit / loop-track / loop-update skills, 2026-06-30). Backed by the claude-loop binary (~/.local/bin/claude-loop, built by claude-tools install.sh). The binary owns every shell op (state JSON, history, locking); the agent only makes the Cron* tool calls. Route on the first argument (the verb):

VerbDoesMechanism
pausePause all active loops; save state for resumeCronList → pipe its JSON to claude-loop pause → CronDelete the returned IDs
resume [interval]Restore paused loops (optional new cadence)claude-loop resume [--interval <i>] → CronCreate ×N from its JSON-line output
stopPermanently stop a loop (delete cron + clear paused state)CronList → CronDelete the entry; clear ~/.claude/.paused-loops.json
editChange interval/prompt without losing the promptCronList (full prompt) → CronDelete <old> → CronCreate with the edits
track <id>Register a raw cron into loop historyCronList (verify id) → claude-loop logs a discovered event
updatePull latest claude-tools + reinstall skills/binariesrun ~/projects/claude-tools/update.sh -f; report which commits arrived
(none)Show current loop statedefer to the loops skill (claude-loop list)

Rules

  • Never inline-truncate prompts. CronList truncates prompts at ~80 chars; for edit / track / resume read the full prompt from the binary's state file, not the truncated CronList view.
  • Each verb is a thin path — 2–3 visible tool calls (one Bash to the binary + the Cron* calls). Let the binary do the file work.
  • pause / resume are symmetric (state in ~/.claude/.paused-loops.json). stop is terminal — no state kept.
  • Pipe every loop prompt through claude-loop prep before CronCreate — it injects the canonical SCHEDULED-LOOP self-check preamble (idempotent), so every fire carries it by construction.
  • Crash-safety lives in claude-loop guard / checkpoint / watchdog; see docs/LOOP_PATTERNS.md.

Don't

  • Don't CronDelete + CronCreate from scratch for an edit — that loses the full prompt unless you pulled it first.
  • Don't append a history event if the Cron* call failed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.