Viewing profile — mksglu

[flagged]

OpenAI published "Harness Engineering" in February 2026. The thesis: engineers don't write code anymore. They design environments, specify intent, and build feedback loops. Agents …

OpenAI published "Harness Engineering" in February 2026. The thesis: engineers don't write code anymore. They design environments, specify intent, and build feedback loops. Agents …

Six days ago I posted a write-up on Hacker News explaining how Context Mode reduces Claude Code's context consumption by 98%. I expected a handful of comments. I got 565 points, 10…

Thanks, really appreciate hearing that! Glad it's working well for your team.

Yeah it's basically pre-compaction, you're right. The key difference is nothing gets thrown away. The full output sits in a searchable FTS5 index, so if the model realizes it needs…

That's the theory and it does hold up in practice. When context is 70% raw logs and snapshots, the model starts losing track of the actual task. We haven't run formal benchmarks on…

That's a fair point and honestly the ideal approach. But in practice most people don't hand-curate their MCP server list per task. They install 5-6 servers and suddenly have 80 too…

It doesn't break the cache. The raw data never enters the conversation history, so there's nothing to invalidate. A short summary goes into context instead of the full payload, and…

Nice approach. Same core idea as context-mode but specialized for your build domain. You're using SQLite as a structured knowledge cache over YAML rule files with keyword lookup. C…

That's true, Claude Code does truncate large outputs now. But 25k tokens is still a lot, especially when you're running multiple tools back to back. Three or four Playwright snapsh…

Haven't looked at rtk closely but from the description it sounds like it works at the CLI output level, trimming stdout before it reaches the model. Context-mode goes a bit further…

Nope. The raw data never enters the conversation history in the first place, so there's nothing to invalidate. Tool output runs in a sandbox, a short summary comes back, and the fu…

Right, context-mode doesn't change how MCP tool definitions get loaded into context. That's the "input side" problem that Cloudflare's Code Mode tackles by compressing tool schemas…

The people who spent years doing the work manually are the ones who immediately see where the bottlenecks are.

Good point on prompt cache invalidation. Context-mode sidesteps this by never letting the bloat in to begin with, rather than snipping it out after. Tool output runs in a sandbox, …

That's pretty much the approach we took with context-mode. Tool outputs get processed in a sandbox, only a stub summary comes back into context, and the full details stay in a sear…

That's exactly what context-mode does for tool outputs. Instead of dumping raw logs and snapshots into context, it runs them in a sandbox and only returns a summary. The full data …