neeeophytee/ai-cost-cutter-skills

1

context-diet Cut agent token spend by shrinking what enters the context window.

neeeophytee/ai-cost-cutter-skills

5

2

route-cheap-escalate-hard Cut LLM spend by routing bulk work to a cheap model and escalating only the hard turns to a premium one. Use when the…

neeeophytee/ai-cost-cutter-skills

5

3

advisor-call-budget Enforce a hard cap and a drift-check when a cheap executor model consults an expensive advisor model, and compute the…

neeeophytee/ai-cost-cutter-skills

3

4

reasoning-effort-throttle Stop paying for deep reasoning on easy turns by setting a modest default reasoning effort and escalating per task.

neeeophytee/ai-cost-cutter-skills

3

5

token-receipts-audit Attribute AI usage by tokens AND dollars so a high-volume cheap model is never mistaken for the expensive one. Use wh…

neeeophytee/ai-cost-cutter-skills

3

6

cheap-swap-guard Before swapping any workload to a cheaper model, declare the cases the premium model still dominates and prove they k…

neeeophytee/ai-cost-cutter-skills

2

7

free-model-triage Route high-volume, low-stakes triage (reading piles, inbox summaries, needs-reply flags) to a free model with a stric…

neeeophytee/ai-cost-cutter-skills

1

8

free-tier-batch-plan Size a big one-time batch job against a free tier's rate limit and token budget BEFORE starting it, with a proven wal…

neeeophytee/ai-cost-cutter-skills

1

9

model-bakeoff Choose a model with evidence by running the few prompts that actually matter across candidate models inside a free ti…

neeeophytee/ai-cost-cutter-skills

1

10

tested-fallback Pin an open-weights fallback model with a tested-on date and real smoke prompts, so a pulled or deprecated model is a…

neeeophytee/ai-cost-cutter-skills

1