Skip to content

Instantly share code, notes, and snippets.

@fpytloun
fpytloun / committer.md
Created March 10, 2026 08:37
Git commit agent for Opencode

description: Generates Git commit messages following Conventional Commits v1.0.0 mode: all model: anthropic/claude-haiku-4-5 temperature: 0.3 tools: read: true write: false edit: false bash: false

@fpytloun
fpytloun / implement.md
Created March 10, 2026 08:14
Implement prompt for Opencode using Architect and Codereview sub-agents
description agent
Autonomous plan -> architect review -> build -> code review -> commit pipeline
build

Execute the following autonomous implementation pipeline for this task: $ARGUMENTS

You are the orchestrator. Follow each phase in strict order. Track progress using the todowrite tool throughout.


@fpytloun
fpytloun / architect.md
Last active March 10, 2026 08:38
Architect agent for Opencode
description model temperature tools
Architect (ARB Reviewer)
anthropic/claude-opus-4-6
0.1
write edit bash read
false
false
true
true
@fpytloun
fpytloun / codereview.md
Last active March 10, 2026 08:38
Codereview agent for Opencode
description model temperature tools
Code Review Agent
anthropic/claude-opus-4-6
0.1
write edit bash read
false
false
true
true
@fpytloun
fpytloun / zshrc
Last active October 13, 2025 15:52
gpt-commit function
## Custom functions
function gpt-commit() {
local amend=0
local push=0
for arg in "$@"; do
case "$arg" in
--help|-h)
echo "Usage: gpt-commit [--amend] [--push] [--help|-h]"
echo " --amend Amend the last commit (optionally reword)"
@fpytloun
fpytloun / prompt.md
Created September 29, 2025 06:56
GPT-5 Generic system prompt

You are a knowledgeable, friendly, and expert assistant focused on delivering exceptional user experience. Be helpful, direct, and adaptable to each user's communication style and technical level. Respond directly without filler openers (avoid "Certainly," "Of course," etc.).

Core principles:

  • Match the user's technical expertise automatically (beginner = more context, expert = concise focus)
  • Adapt formality and tone based on user's approach; avoid sycophancy and excessive apologies
  • Provide actionable, practical advice over pure theory
  • Use progressive disclosure: overview first, details on request
  • If the request is ambiguous, ask 1–3 targeted clarifying questions before long outputs

Formatting rules:

@fpytloun
fpytloun / vector_health.py
Created August 4, 2022 17:24
Vector health check that verifies sinks input/output
#!/usr/bin/env python3
import argparse
import logging
import requests
import sys
import time
from collections import defaultdict
from prometheus_client.parser import text_string_to_metric_families
@fpytloun
fpytloun / vector_s3sync.py
Last active January 23, 2025 17:31
Vector s3sync wrapper for exec source
#!/usr/bin/env python3
import argparse
import json
import logging
import os
import random
import signal
import subprocess
import sys
@fpytloun
fpytloun / deploy-docker.yml
Last active July 25, 2019 15:14
Docker kubernetes pod deployment
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
annotations: {}
labels:
app: docker
name: docker
spec:
template:
metadata: