qualixar

Slm Loop — Productivity skill for Claude Code

Productivity community

Run a task as a bounded, gate-verified loop backed by SuperLocalMemory — iterate until an independent gate passes, never on the agent's own claim.

How to install Slm Loop

Installs to ~/.claude/skills/qualixar-superlocalmemory-plugin-slm-loop/SKILL.md

Terminal

mkdir -p ~/.claude/skills/qualixar-superlocalmemory-plugin-slm-loop && curl -fsSL https://raw.githubusercontent.com/qualixar/superlocalmemory-plugin/HEAD/commands/slm-loop.md -o ~/.claude/skills/qualixar-superlocalmemory-plugin-slm-loop/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Slm Loop does

description: Run a task as a bounded, gate-verified loop backed by SuperLocalMemory — iterate until an independent gate passes, never on the agent's own claim. argument-hint:

Run this task as a **bounded loop** using SuperLocalMemory as the durable ledger:

$ARGUMENTS

Delegate the execution to the **slm-loop-runner** agent and follow the **slm-loop** skill. The one rule is non-negotiable: the loop

Alternatives in Productivity

Chief — CLI that wraps Claude Code in a loop 396 ★
Adversarial Execution — Adversarial Execution — an execution-time review gate: two independent strong models must both prove your work 28 ★
Bead Workflow — Flywheel bead lifecycle workflow — claim, implement, review, and close beads following the Agentic Coding Flyw 23 ★