KiloClaw is amazing.
A practical field guide for routing KiloClaw/OpenClaw model calls through a ChatGPT Plus/Pro Codex OAuth session instead of a traditional OpenAI API key.
KiloClaw normally makes model calls through configured model providers. The regular openai provider expects an OpenAI API key and bills through the OpenAI API platform.
Someone asked me about using Claude Code for huge codebases, including legacy systems in Ada. I had mentioned that the key seems to be able to make these large code bases modular enough so that both LLMs and humans can reason about them.
You had mentioned experiments you had done with LLMs making changes to Chromium, a code base that is similar in size to this particular code base.
I had made the claim that LLMs seem to do an amazing job understanding large code bases, and suspected they could do the equivalent of summoning Michael Feathers (author of "Working Effectively With Legacy Code") — if it could advise on how to split a large system into two smaller systems, it could recursively be able to partition large systems into manageable smaller systems.
Here is the output of a quick experiment. Literally a handful of prompts: "clone the Chromium repo," "summon your inner Michael Feathers and find natural seams where we can further modularize the codeba
After watching the Clojure/conj 2025 talk on ECA, I was inspired to try using the clojure-lsp plugin. I stumbled upon the cclsp MCP server, which seemed like the ideal way to use this with Claude Code.
Enclosed below are all the instructions necessary to get them both up and running.
My high-level impressions:
I'd love to hear your thoughts!
LLMs frequently emit malformed S-expressions (unbalanced ()[]{}) when generating Clojure/EDN/Lisp code. Post-hoc “repair” is surprisingly difficult. Saving source code files with balancing errors, or streaming them to nREPL/compilers, wastes time and relies on imbalance detection after the tokens are generated.
What if we could prevent these types of error by creating a tool (stateless, stack-based, cursor-aware) for LLMs to use to help them write perfectly balanced S-expression. Ideally while minimizing latency, round-trips, total time required to generate code, and without any MCP server-side state.
Current LLMs are inherently auto-regressive auto-completers, which makes them inherently bad at the problem of closing S-expressions -- they don’t have anything resemblig a “stack” for them to store state (e.g., I just emitted an open parenthesis, and here’s an open bracket. I want to close the form — now what?). Nor does it have an equivalent of a “find
I've been compiling this document for a couple of weeks, with the intent of publishing it, to at least advertise this problem I've been struggling with. One that has been bothering me enough where I've done a ton of little experiments to see if I can ameliorate it, even by a little!
Then just now, I was talking with my friend Scott Prugh who was just complaining about something in Python, and he was lamenting how he wanted to do things in C#. I asked him why, and he was complaining about the same problem that I've been having!
The problem: LLMs will often hallucinate map keys that don't exist. He and I commiserated about how we both spent hours trying to hunt down a problem that would have been solved if there were a data structure more like a class or a struct in C, where you could generate an immediate error if trying to get or set a value that doesn't actually exist.
| # Java proxy configuration for local proxy shim | |
| # Source this file before running Maven/Gradle/Clojure builds | |
| # | |
| # Usage: . ./.proxy-java-shim.env && mvn test | |
| export JAVA_TOOL_OPTIONS="-Dhttp.proxyHost=127.0.0.1 -Dhttp.proxyPort=15080 -Dhttps.proxyHost=127.0.0.1 -Dhttps.proxyPort=15080" | |
| export MAVEN_OPTS="$JAVA_TOOL_OPTIONS" |
Fantastic—here’s a compact, copy‑pasteable doc you can hand to tech‑leader participants. Every dataset below is (a) free, (b) downloadable for local/offline analysis on a dev‑class laptop, and (c) has a clear “what it’s good for.” I include at least one option for each topic you asked for, plus a bonus section with public backlogs/tickets/incident datasets.
Primary (recommended): The Public Jira Dataset (anonymized, 2025 release)
⏺ The instructions for retrieving Claude Code prompts are in /Users/genekim/src.local/mdparse/docs/claude-code-logs.md. Key locations:
Primary data storage:
To find your prompts:
ls -la ~/.claude/projects/
When trying to use expo-av’s Audio.Sound class in a ClojureScript React Native app (using shadow-cljs), we encountered a persistent error:
TypeError: Cannot read property ‘prototype’ of undefined
This error occurred when trying to:
A fast Babashka script for interacting with the running nREPL server. Located at server/nrepl.clj.
The script automatically reads the port from .nrepl-port file.
Command line argument (fastest for one-off commands):
./nrepl.clj '(+ 1 2 3)'
./nrepl.clj '(require '\''[podcast.db :as db]) (count (db/get-recent-episodes 10))'