Tag: token-optimization
All the articles with the tag "token-optimization".
-
Cutting Rules to Save Tokens: One Week of AI Harness Ablation
Most people keep piling instructions onto their AI, but removing rules is what actually saves tokens. Here are the one-week results of my ablation experiment and how Anthropic recommended the exact same thing.
-
I Built an Exam From My Own Chat Logs and Retake It With Every New Model
I turned the work I hand to AI every day into a private exam, then used it over three weeks on Claude at different effort levels, Gemini, Codex and open models. How the questions are made, how each round runs, how scores become routing rules, and prompts you can copy.
-
Burning and Saving AI Quota: How I Audited, Allocated, and Spent My Compute
An audit of seven AI quota pools: burning expiring credits on self-verifiable tasks while using surplus compute to build long-term token savings. Combines a terminal dashboard and routing scripts to dispatch tasks dynamically and refine rules from logs. Includes complete tables and reusable prompts.
-
Two Claude Mods I Built: a Recording Mask and a Warm-Cache Plugin
I built two Claude Mods: one that masks sensitive info while I record courses, and one that keeps the Claude Code prompt cache warm. Then I found Claude Code already has idle compact built in.
- Updated:
Letting an Agent Tune a Local Video Model Overnight: My Three Gates
Three things I learned from letting an agent run local video-model parameter research overnight: hard constraints in CLAUDE.md, a gate script watching SSD writes, and a 30-minute check-in loop.
- Updated:
When to Call In Fable: Three Moments, and Don't Turn On ultracode
The most expensive model is not meant to run the whole way. Three moments where calling in Fable feels right to me, plus why I cap Opus 5 at med, and the weekly cycle I fell into: efficiency king Monday to Thursday, Fable mode Friday to Sunday.
- Updated:
Where the Quota Actually Goes: Claude Code Cache Bugs, Opus 4.7's 2x Burn, and Runaway Subagents
Four quota incidents in full: two official cache bugs, an 80x jump in API requests pulled from JSONL, Opus 4.7 measured at 2x consumption, and one session of mine that burned 90% in half an hour.
- Updated:
The More Rules You Add, the Less Claude Listens: Trimming 36% of Baseline Context with an AI Fleet
Piling on rules makes LLMs miss what actually matters. When a 1M context window gets clogged with noise, you need an overhaul. Here is how an automated team of subagents trimmed my baseline harness by 36% by stripping out narrative fluff and conflicting constraints.
-
Digging into Claude Code's JSONL: Manual Context Usage, Cache Types, and Compact Detection
Claude Code's `/stats` only tells you the total token count, but the JSONL files hide a lot more—cache types, compact triggers, image-triggered cache misses. Here are the useful formulas I collected while building cc-audit.
-
cc-audit: A Skill That Stops Claude Code from Burning Your Tokens
I turned my viral token-saving tips into an automated audit skill for Claude Code. Feed it to Claude Code, and it inspects your settings, recent sessions, rules, and context usage to hand you an actionable checklist of fixes.