token-frugal-engineeringlisted

# Token-Frugal Engineering ## Overview The expensive resource is **main-context tokens**, not wall-clock. Every file dumped, log scrolled, or option narrated burns budget you can't get back. This skill is the distilled discipline for spending tokens where they buy correctness and nowhere else. **Core principle:** Keep verbose, low-signal work OUT of main context. Pull only the conclusion in. **Announce at start (long/heavy tasks):** "Using token-frugal-engineering to keep context lean." ## The Essence Rules | # | Rule | Why | |---|---|---| | 1 | **Delegate verbose work to subagents** — *when output is bulky AND you need only the verdict*: tests, builds, log scans, broad searches, doc fetches. Instruct the agent to return capped, structured output ("≤10 lines, failing names only"). | Raw output never lands in main context. Skip for a short log/tiny suite — agent overhead beats the savings there | | 2 | **Search, don't read** — Grep/Glob to locate; never `cat`/`find`/whole-file reads to explore | A read pulls the whole file; a grep pulls 3 lines | | 3 | **Scoped reads** — Read with offset/limit on the part you need | Don't load 2000 lines for one function | | 4 | **Don't re-read to confirm a write landed** — Edit/Write already errors on failure; harness tracks state. *Legit verification reads (did the logic come out right after a tricky multi-edit) are fine.* | Confirm-reads are pure waste; correctness-reads are not | | 5 | **Plan before code** on non-trivial tasks | Misd