serpro69

#!/usr/bin/env python3
"""
cc-sessions — Fast CLI to search, browse & resume Claude Code session history

OVERVIEW
--------
Claude Code stores all conversation history locally in ~/.claude/projects/ as JSONL files.
This tool indexes those sessions for fast search and provides a clean CLI interface to:
  - Search by keyword across all conversations
  - Filter by date, branch, or project

serpro69

{"parentUuid":null,"isSidechain":true,"promptId":"ae131cdb-7ea1-43cd-aea7-8b867c8ed6e5","agentId":"a170fb21fbbd73e4e","type":"user","message":{"role":"user","content":"I need to understand the current session parsing and indexing implementation in the capy project at /Users/sergio/Projects/personal/capy.\n\nSpecifically, I need to find and read:\n\n1. `internal/session/parse.go` — The JSONL parser. I need to understand:\n   - How it filters messages (what's kept, what's skipped)\n   - How it handles `tool_use` blocks (currently only extracts tool names, drops content)\n   - How it handles MCP tool calls like `mcp__pal__chat`\n   - The `TurnPair` and `ParsedSession` types\n   - The progressive snapshot merging logic\n\n2. `internal/session/transcript.go` — How the transcript is built from parsed data\n\n3. `internal/session/chunk.go` — The chunking strategy (window size, overlap)\n\n4. `internal/session/sweep.go` — The sweep orchestration\n\n5. Any test files in `internal/session/` that show what test fixtures

serpro69

{"type":"permission-mode","permissionMode":"default","sessionId":"b5ee5362-8700-4c9c-8278-51cb58c2e096"}
{"parentUuid":null,"isSidechain":false,"attachment":{"type":"hook_success","hookName":"SessionStart:startup","toolUseID":"5bbd32f1-a1da-4c40-a9b2-d774b2529958","hookEvent":"SessionStart","content":"","stdout":"{\"hookSpecificOutput\":{\"additionalContext\":\"\\u003ccontext_window_protection\\u003e\\n  \\u003cpriority_instructions\\u003e\\n    Raw tool output floods your context window. You MUST use capy\\n    MCP tools to keep raw data in the sandbox.\\n  \\u003c/priority_instructions\\u003e\\n\\n  \\u003ctool_selection_hierarchy\\u003e\\n    1. GATHER: capy_batch_execute(commands, queries)\\n       - Primary tool for research. Runs all commands, auto-indexes, and searches.\\n       - ONE call replaces many individual steps.\\n    2. FOLLOW-UP: capy_search(queries: [\\\"q1\\\", \\\"q2\\\", ...])\\n       - Use for all follow-up questions. ONE call, many queries.\\n    3. PROCESSING: capy_execute(language, 

serpro69

I wanted to try the new Opus 4.7 on a small personal project of mine and gave it a simple github issue to explore - serpro69/claude-toolbox#77 My first session with the new model, and while the agent was doing the exploration, its first response was "I'll ignore the task tools reminder as noted. Let me keep exploring."

I dug into what it meant by that statement, it and it gave me its entire system prompt ¯_(ツ)_/¯

The full dump is available here: https://github.com/serpro69/claude-toolbox/tree/master/docs/wip/system-prompts

serpro69

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

serpro69

Claude Code Mastery: Advanced Patterns for 10x Productivity

A comprehensive guide to the patterns that actually move the needle

Reverse-engineered from 2000+ hours of LLM-assisted coding

---

Table of Contents

serpro69

Export of my own styles for the Stylus chrome extension.

serpro69

Sure! Here's a large, complex README.md file example that includes:

• Project overview
• Features list
• Installation instructions
• Usage examples
• Mermaid diagrams (flowchart & architecture)
• HTML styling (colored text, badges, tables)
• Code blocks (with language highlighting)
• Contribution guidelines

serpro69

If you're using a high-end bluetooth headset on your Macbook Pro it's likely your mac is using an audio codec which favors battery efficiency over high quality. This results in a drastic degradation of sound, the SBC codec is the likely culprit, read more about it here.

Find out what codec you're using

1. Play a song on your headphones
2. Option (⌥) click the Bluetooth button at the top of your screen
3. If you're using AAC or aptX, you can stop here—those are the highest quality codecs.

Change your codec to AAC or aptX

serpro69

#!/bin/bash

set -e

show_help() {
  echo "Usage: ./test.sh <REPO_OWNER> <REPO_NAME> <WORKFLOW_ID> <COMMIT_SHA>"
  echo ""
  echo "This script polls the status of a GitHub Actions workflow run."
  echo ""
  echo "Arguments:"