githubcopilotlisted

# Copilot Review A second model reads the diff. The point is a different reviewer rather than a better one: Claude re-reading its own work shares the blind spot that produced it. It has already caught an unchecked-failure defect that two Claude review passes both cleared. ## What It Costs The plan grants 1500 AI credits a month. It resets on the 1st and does not roll over. Four measured facts shape every choice: - A terra call pays about 3.5 credits before it reads a line of your code, writing 14k tokens of system prompt and tool definitions to cache at 250 credits per million. That is half a median review. A second call is never a rounding error. - Output costs 6x input and 60x cache_read. Verbose answers run up a bill faster than large diffs. - Nothing caches between calls. Separate spawns are separate sessions, and each one re-pays its whole prompt at the cache_write rate. Three angles cost three full prompts. - `gpt-5.6-luna` prices every token class at exactly a tenth of terra. ## Sizing a Review `--status` prints the current tier and the bands, and spends nothing. Run it when you are unsure whether a change qualifies. The tier comes from `pace`, credits remaining divided by days to reset. Under 25 is constrained, over 60 is abundant, and everything between is normal. The nominal allowance of 48 a day (1500 over 31) is the yardstick `--status` prints `pace` against, and it decides nothing on its own. The tier sets how strict the bar is, never how much to spend. Ma