P

prompt-engineering

Free LLM token counter: see how GPT-4 and GPT-4o split your prompt into tokens, which lines cost the most, and which wordy phrases to cut, with savings measured by re-tokenizing. Runs offline on Linux, macOS and Windows. Uses tiktoken.

💬 Epic prompts to turbo-charge your LLM chatbots.

Free in-browser token counter: see every token for GPT-5, GPT-4o, GPT-4, Llama 3, Qwen3, DeepSeek, Mistral, rank lines by cost, cut wordy phrases. Nothing uploaded. Live at gpt-token-counter.vercel.app

Rank the lines of a prompt by token cost and fail CI when a prompt goes over its token budget. Offline, uses OpenAI's tiktoken. Python CLI.

GitLab CI/CD components for LLM apps: fail the pipeline on likely hallucinations, prompts over their token budget, padded prompts, an LLM bill heading over budget, or slow and flaky models. Tested on every push.

Single-header C++17: Mustache-style prompt templates with loops, conditionals and token-budget truncation. Part of llm-cpp.

claude by router use SKILLS

anti-slop vision gates: prompt hygiene + VLM judge rubric (SHIP/FIX/REGEN)

Describe an AI agent, get a ready-to-run agent home with persona, memory and a growth loop. Build one agent or a whole collaborating team.

Sharpen the axe before cutting wood - fool-proof requirement clarification skill for AI agents (Claude Code / Cursor / any LLM)

ThreadGraph is an open-source, AGPL-3.0+ modular agent swarm runtime that transforms complex tasks into executable, graph-structured workflows. It orchestrates multiple specialized agents, tools, and memory systems through a dynamic execution graph, enabling parallel reasoning, structured decomposition, and fully observable workflows. Designed for extensibility and composability, ThreadGraph turns agent-based systems into scalable, reproducible infrastructure rather than linear prompt chains. https://roxanneardary.com/threadgraph/

Guideon IA is a local control layer for AI-assisted development. It standardizes how coding agents read project context, skills, permissions, model profiles, memory settings, and workflow rules, making agent-based development more reproducible, auditable, and portable across tools.

Shared AI prompt library for the ValkymIA team

AI Code Reviewer for GitLab CI — An automated, LLM-powered code-review system that runs inside GitLab CI on every Merge Request. The reviewer analyzes changed files using Azure OpenAI, detects bugs, code smells, risky patterns, and quality issues, and generates structured HTML/JSON reports stored in CI artifacts.

All review logic is contained inside the ci/ folder, and the .gitlab-ci.yml pipeline securely fetches only the MR target branch to perform the analysis. No external servers or deployments required — the entire review happens within GitLab CI.

A Rag application that keeps you updated about AI news, scrapped from MIT AI newsletter website