better-loop

better-loop is a plugin for Claude Code from fledgeling-co/fledgeling-plugins. Its manifest loads nothing; the 1 skill it bundles cost 301 tokens per session together, scanned A, original, MIT.

A change-aware watcher for recurring or event-driven work. It checks a deterministic command in the background and wakes or dispatches work only when the checked state changes.

In plain words
What is it for?
Monitoring files, services, or other command-based conditions; sending only changes to an agent; and handing tasks with a verifiable endpoint to a goal-tracking workflow.
Why use it?
It avoids repeatedly sending the same unchanged problem to an agent and includes safeguards for repeated states, wake limits, stopped watchers, and work with a clear finish condition.

Plugin for Claude Code

Written for Claude Code: SessionStart hook event.

Good fit Monitoring files, services, or other command-based conditions; sending only changes to an agent; and handing tasks with a verifiable endpoint to a goal-tracking workflow.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add fledgeling-co/fledgeling-plugins
/plugin install better-loop
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for better-loop

README.md
[![agentmods](https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/better-loop/github.svg)](https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/better-loop)
Your own site
<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/better-loop"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/better-loop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for better-loop

Your own site · 80×15
<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/better-loop"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/better-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 301 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

better-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/better-loop/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "better-loop",
  "description": "Arm recurring or event-driven work as a change-gated watcher this skill creates itself, so a tick fires only when something has actually changed. A scheduled loop re-sends the same unmet condition and the same failing tasks turn after turn, re-billing the session's whole prefix each time: five of twelve measured heavy sessions did exactly that and accounted for 91% of input between them. better-loop:better-loop (formerly loop-harness) polls a deterministic probe command in the background, wakes the session only on a change and sends the delta rather than the state, backs off on a state it has seen before, holds a wake budget per hour, and can dispatch the tick detached so the session is never woken at all. It picks the mechanism first, preflights the probe for determinism and the skills the tick names, and routes to better-goal:better-goal when the work has a verifiable finish line. No cron, so no seven-day expiry. Because a Monitor dies with the session that started it, it stamps a heartbeat on every poll and registers a SessionStart sentinel, so a loop that stopped is reported to the next session rather than reading armed forever.",
  "version": "2.2.2",
  "author": {
    "name": "Fledgeling",
    "email": "[email protected]"
  }
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 301 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago Changed 58c1aa4e2861
  2. 1mo ago Changed 75a01f873136
  3. 1mo ago First seen · 10 lines scan A f8f7201cfa2f

Subscribe to this mod's changes

better-loop is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.