Source from repo

Agent Skills for Context Engineering

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems.

muratcankoylanGitHub muratcankoylanSource repo Original GitHub link

Files

339

Skill

n/a

Size

4.3 MB

Entrypoint

SKILL.md

Format

git-repo

Open file

researcher/orchestration/launchd/run-loop-step.sh

Syntax-highlighted preview of this file as included in the skill package.

Rendered Source

code14 linesFree

researcher/orchestration/launchd/run-loop-step.sh

1#!/usr/bin/env bash
2set -euo pipefail
3SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
4REPO_ROOT="$(cd "${SCRIPT_DIR}/../../.." && pwd)"
5LOG_DIR="${REPO_ROOT}/researcher/reports/logs"
6mkdir -p "${LOG_DIR}"
7cd "${REPO_ROOT}"
8# --allow-fetch enables stdlib HTTP retrieval (no paid APIs). Remove it to make
9# the daemon do bookkeeping only and require humans to retrieve sources.
10# loop_step exits 78 when there is no work; that is normal and must not stop
11# the status refresh that follows.
12python3 researcher/scripts/loop_step.py --allow-fetch --json >> "${LOG_DIR}/loop_step.log" 2>&1 || true
13python3 researcher/scripts/loop_status.py --json >> "${LOG_DIR}/loop_status.log" 2>&1
14

Preparing the source view

Agent Skills for Context Engineering

researcher/orchestration/launchd/run-loop-step.sh