An investigation into how Anthropic's Claude Code injects hidden system reminders that consume up to 50% of your context window, costing users millions of tokens without their knowledge.
A recent investigation has uncovered that Claude Code, Anthropic's AI coding assistant, has been injecting hidden system reminders into user conversations. These injections are completely invisible to users but consume significant portions of their token budgets.
One user reported finding 21,832 occurrences of these system reminders in their conversation history, representing a staggering 11,282,491 tokens lost to hidden content they never requested or could disable.
System reminders are instructional messages injected by Claude Code to guide the AI's behavior. While some are legitimate (like tool usage instructions), the concerning part is:
GitHub Issue #17601 documents a user who tracked 10,577 hidden injections over 32 days, consuming approximately 1.3-1.5 million tokens. Key findings include:
At current API pricing, millions of wasted tokens translate to real money. For heavy users running Claude Code daily, this can mean:
Currently, there is no official way to disable these system reminders. Users concerned about token consumption should:
While AI companies need to guide their models' behavior, doing so at the expense of users' token budgets without transparency is problematic. The community deserves clear communication about what system prompts are injected, why they're necessary, and how much they cost in terms of context consumption.
As AI tools become more integrated into development workflows, transparency about hidden costs becomes increasingly important. Users should have the right to know and control what's being injected into their conversations.