pnkd.dev
dev tools with attitude
// glitch the system. break the prompt.
// tools
stuff your context. pack entire directories into LLM-ready format. .gitignore aware. token estimation included.
📦 18.4k installs
⭐ 1.2k
available
compare prompt versions. track changes. see what broke your AI.
📦 9.7k installs
⭐ 678
available
local LLM response cache. stop paying for the same API calls. hash-based dedup.
📦 12.1k installs
⭐ 892
available
token counter for all models. GPT, Claude, Gemini. know your context limits.
📦 21.3k installs
⭐ 1.5k
available
local proxy for LLM APIs. logging, rate limiting, cost tracking. own your data.
📦 7.8k installs
⭐ 534
available
split large contexts intelligently. semantic chunking. overlap control.
📦 6.4k installs
⭐ 423
available
// at a glance
| tool | what it does | size | deps |
|---|---|---|---|
| ctxstuff | pack directories for LLMs | 24kb | 0 |
| promptdiff | compare prompt versions | 18kb | 0 |
| pnkd-llmcache | cache LLM responses | 28kb | 1 |
| pnkd-tokcount | count tokens | 32kb | 1 |
| pnkd-aiproxy | LLM API proxy | 45kb | 2 |
| pnkd-ctxsplit | split contexts | 20kb | 0 |