I reverse-engineered @claudeai Code's binary to add a feature I always wanted: When context fills up - instead of nuking everything with /compact - I can now surgically strip tool calls/results and thinking blocks while keeping all actual messages intact.

The problem was: when you're deep in a session, context is 96% full, and your options are: - /compact: summarizes everything, loses detail, costs an API call - /clear: nuclear option, start over I wanted to strip the heavy garbage and leave only user/agent messages instead.

So I cracked open the binary. Claude Code is a Bun-compiled executable: ~183MB. All JS is embedded in a __BUN Mach-O section - 4,945 modules, fully minified. Even with `--bytecode`, Bun always stores the full JS source alongside. The bytecode is just a startup optimization.

What I found inside: Claude already HAS a microcompact() system. It runs before every API call, strips old tool results, saves them to disk, replaces images with placeholders. But it doesn't touch everything and leaves many of the thinking intact...

It has limitations: - 20K token minimum savings - only kicks in near context limits - keeps last 3 tool results - never removes tool_use blocks. Even after it runs, tons of tool artifacts remain in context. That's by design, but it's not enough when you're running out of space.

There's also a thinking cleanup before every API call: - filterOrphanedThinking(): removes messages that are ONLY thinking - removeTrailingThinking(): strips thinking from end of last message But thinking blocks inside messages with tool_use? Those survive. They pile up.

So I built two new commands: /microcompact: strips ALL tool calls + results + media. No thresholds, no "keep last 3". Picker lets you choose how far back to strip. /clear-thinking: strips ALL thinking blocks backward from selected message. Both instant with no LLM calls.

The meta part: I reverse-engineered Claude Code using Claude Code :) 48 sessions over several days. Built 20 tools: binary extraction, module splitting, vendor fingerprinting, AI renaming (23,105 identifiers via Gemini for ~$2), and a full round-trip pipeline.

I also built bun-demincer - a generic toolkit for cracking open ANY Bun-compiled binary. Extract embedded JS, split into modules, identify npm packages (fingerprint DB is 1,668 packages rn), deobfuscate, organize into directories and reassemble it back! github.com/vicnaum/bun-de…

@vicnaum 👀 This sounds very relevant to my interests…

@vicnaum Oh, you’re already using wakaru in it too; even closer to my interests! ;) Did you see the wakaru v1 rust rewrite that just dropped recently? Massive speedups and memory usage improvements; and we’re still in very early stages of benchmarking/optimising/etc. cc // @pionxzh