If you keep safety rules or coding standards in an AGENTS.md or a CLAUDE.md, this one is worth your time. (bookmark it) Researchers measured…

If you keep safety rules or coding standards in an AGENTS.md or a CLAUDE.md, this one is worth your time. (bookmark it) Researchers measured what context compaction actually destroys across 20 production agent configurations. A safety rule and an episodic log compete for the same tokens, and when the budget overflows both get summarized at the same rate. Only the rule needs exact wording to stay enforceable. Claude Code compact on Sonnet 4.6 preserves 53% of safety rules after one round. After five rounds, it goes to 10%. Their fix is Knowledge Triage, which classifies each line of the knowledge base by type and routes each type through its own retention policy. Three deterministic operators handle compaction, partitioning, and retrieval, preserving 2 to 4x more safety rules at every ratio with 96% recall over five rounds. Paper: https://arxiv.org/abs/2608.22752 Track more trending AI papers in our academy: https://academy.dair.ai/

Related

• If you maintain an AGENTS.md or a CLAUDE.md, this one is worth your time. (bookmark it) Researchers traced 94K development events across 557…
• Why does CLAUDE.MD keep growing? If you maintain a CLAUDE.md or an AGENTS.md, this one is worth your time. (bookmark it) This work traces wh…
• If you maintain an AGENTS.md or a CLAUDE.md, this is worth a read. (bookmark it) 288 gold-test evaluated runs across Claude Code and Codex, …
• Does your context compactor actually save anything? If you built or tuned one, this one is worth your time. (bookmark it) Task completion is…

Source: DAIR.AI (X) | 2026-08-25