Wednesday, April 15, 2026
Daily picks
20
articles scored
#1 GOLDReleaseClaude Code Releases
v2.1.108
- 1-hour prompt cache TTL is now opt-in with `ENABLE_PROMPT_CACHING_1H` — previously API key users (and anyone who set `DISABLE_TELEMETRY`) were silently capped at the 5-minute TTL, burning extra cost on long sessions
- New `/recap` command summarizes what happened since you stepped away so you can resume context instantly without re-reading the full transcript
- Claude can now discover and self-invoke built-in slash commands like `/init`, `/review`, and `/security-review` via the Skill tool — opens the door to agent workflows that trigger standard operations without manual prompting
- Error messages are now meaningfully differentiated: rate limits vs plan limits are separate, 5xx/529 errors link directly to status.claude.com, and unknown slash commands suggest the nearest valid match
- `/resume` defaults to sessions in your current directory; Ctrl+A expands to all projects
#2 SILVERGuideDev.to Claude
YAML vs Markdown vs JSON vs TOON: Which Format Is Most Efficient for the Claude API
- The same 200-product catalog costs 15,879 tokens in JSON vs 6,088 in TOON — a 62% difference that hits your API bill every call
- This is the first public benchmark run on Claude specifically (Haiku 4.5, Sonnet 4.6, Opus 4.6): 450 API calls, 120 data files, 8 real-world scenarios, Anthropic's production tokenizer
- Practical rule: prefer Markdown or TOON over JSON whenever you're passing structured data as context — not just in prompts, but in tool responses and retrieved documents
#3 BRONZEGuideDev.to Claude
Context budget optimization: how to design MCP tools that don't waste tokens
- Most MCP tools return raw API JSON (4,000+ tokens) when Claude only needs a pre-digested summary — a 10-100x token waste per call
- Design MCP responses to include what changed, what it means, and what to do next — not raw data dumps