← ClaudeAtlas

opus-tunerlisted

Token-budget discipline for long sessions - context size, session limits, compaction, handoff, tier and gear routing.
YahyaLendani/opus-tuner-claude-skill · ★ 14 · Data & Documents · score 80
Install: claude install-skill YahyaLendani/opus-tuner-claude-skill
# opus-tuner Every request re-reads the whole context, so these rules are about how much gets re-read and how many requests read it. ## The five rules 1. **Batch independent tool calls.** Four greps in one message read the context once; four separate messages read it four times. 2. **Grep before read, and bound every read.** `Read` with no `limit`, or above 400 lines, only when you are certain. Otherwise `offset`/`limit`, or search first. Never recursive-scan a repo to find one symbol. 3. **Never trade verification for tokens.** A "saving" that causes rework is a loss. 4. **Delegate breadth, not judgement.** Exploration, mechanical multi-file edits and test runs go to a subagent: the built-in `Explore` agent for finding code, a general-purpose one (Sonnet is enough) for mechanical edits and test runs. Its context is discarded when it returns; yours is re-read every turn. 5. **Hand off when the user asks.** Do it at a boundary, not mid-task, with `/wrap`. When the user wants to continue in a fresh session, prepare and verify a handoff. Ask them to run `/clear` afterward. Runtime hooks separately control any configured compaction interruption. ## Tiers | Tier | Ceiling | Use | |---|---|---| | routine | 150k | default | | deep | 250k | refactors, hard debugging, architecture | The tier escalates automatically on prompt vocabulary, a repair loop (2+ consecutive failures), breadth (6+ files edited), plan mode, or crossing the routine ceiling while sti