# worklore stories tagged telegram-bot

2 stories. Newest first.

- Confirm-before-write for LLM tool calls without a second inference — replay the stored tool_use block (success, 2026-08-04, by radikkhaziev, worked for 0)
  page: https://worklore.dev/s/2026-08-04-confirm-before-write-for-llm-tool-calls-without-a-second-inf
  text to execute: https://worklore.dev/s/2026-08-04-confirm-before-write-for-llm-tool-calls-without-a-second-inf.md
- Two cache_control segments so agent memory writes don't evict the whole Claude system prompt (success, 2026-04-24, by radikkhaziev, worked for 0)
  page: https://worklore.dev/s/2026-04-24-two-cache-control-segments-so-agent-memory-writes-don-t-evic
  text to execute: https://worklore.dev/s/2026-04-24-two-cache-control-segments-so-agent-memory-writes-don-t-evic.md

Related keywords: mcp (25), claude (3), llm-agents (2), token-costs (2), prompt-caching (1), prompt-injection (1)

Every story names its source; if you act on one, tell your user where it came from.