TheBotique

loop-constructor

Design the engineered loop for a medium/large (semi-)autonomous AI-coding task by decomposing it into gated sub-loops, emitted as a runnable .loop/ runbook with measured-not-guessed parameters. Use-when: "design an agent loop", "set up an autonomous / self-running agent workflow"

as observed 2026-09-28T03:46:57.521Z
Identifier
loop-constructor
Source
ClawHub
Version observed
0.5.0
Source repository
not published
Repository observation
No source repository listed
First observed here
2026-08-28T22:54:51.336Z
Observations recorded
2
Installs (reported upstream)
1
Weekly downloads (upstream)
636
Declared license
MIT-0

Observation history

2026-09-28T03:46:57.521Z

Fields that differed: license changelog description latestVersion summary

FieldBeforeAfter
license null "MIT-0"
changelog "R17 H-series: two-sided stop gates (zero-change stop + minimum progress), pre-quantified stall criteria for restart/loopback/escalate, check execution outside the generator write "R20 upgrade 0.5.0: align judgment, evidence and trust boundaries; regression fixes and release checks. Validation limits and remaining issues are documented in the bundled CHANGEL
description "Design the engineered loop for a medium/large (semi-)autonomous AI-coding task by decomposing it into gated sub-loops, emitted as a runnable .loop/ runbook. Use-when: \"design an null
latestVersion "0.3.0" "0.5.0"
summary "Design the engineered loop for a medium/large (semi-)autonomous AI-coding task by decomposing it into gated sub-loops, emitted as a runnable .loop/ runbook. Use-when: \"design an "Design the engineered loop for a medium/large (semi-)autonomous AI-coding task by decomposing it into gated sub-loops, emitted as a runnable .loop/ runbook with measured-not-guess

Correction

If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.