Tag: harness
All the articles with the tag "harness".
-
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.
-
My AI's Memory Files Kept Growing, So I Deleted 101 and Added a Gate
After a few months with Claude Code, the memory files it wrote for itself had piled up past four hundred, mostly running logs and client status. Here is how I sorted them, cut them to just over three hundred, and put a write gate in front to stop the regrowth.
- Updated:
Having Claude Dig Through a Month of My AI Chats: Habits, Mods, and Auto Mode Rules
I asked Claude Code to sift through over 300 chat logs from the past month to extract four collaboration habits, turn my most frequent catchphrases into switchable modes, and refine auto-review rules using real rejection cases.
-
Switching Your AI's Working Mode with One Command: Building work-mode and a Week of Testing
I built work-mode, a Claude Code plugin with autonomous, delegate and wrap-up modes plus desktop/phone reply formats. The pain points, how it evolved, numbers from 136 sessions, and prompts you can copy.
-
I Asked My AI "Now What?" 41 Times in Two Weeks
Letting an AI run long jobs in the background is easy. Knowing where it got to when you come back is not. I counted two weeks of my own messages and found I was missing a status board, not more monitoring.
-
A Rule Being Written Doesn't Mean It Got Read
Writing a rule or skill into a file does not mean the model opened it this turn. Two lesson-prep misses this week, plus magpie's lessons-file approach, show why the call site has to say "open and read this first."
-
159 Confirmation Prompts in 14 Days, and About 70% Were False Alarms
I audited 14 days of PreToolUse hook ask prompts: 159 of them, roughly 70% false positives. A guard hook should match the command position, not the whole string, and you can measure the fix from hook events in the transcript without replaying anything.
-
Keys Leak Where You Feel Safe
Three near-leaks of API keys in one week, and none came from pasting one somewhere public: skill packaging, a masking command that failed, and a build config. Plus the rule I use to decide whether to rotate.
-
Where JEV Fits: Four Ways I Use It and Three Criteria
JEV is a new model that only does probability judgments and formatted output, fast and cheap. I swapped it into the semantic gates I used to run on luna and flash-lite, plus harness slimming, news filtering, and exam-question QA.
- Updated:
The Skills and Hooks I Use Every Day, Now Open Source
I open-sourced the Claude Code skills and hooks I actually use every day. No technical skill required, pure logic, built for knowledge workers with no coding background.
-
How to Write a Gate That Actually Blocks
The gate was running and stopped nothing. Four rules: bind it to a field that cannot survive a no-op, counter-test both directions before trusting a zero, exit non-zero or it is not a gate, and never treat wording the prompt never specified as a contract.
-
Proving Absence Is Much Harder Than Proving Presence
Four times this week my agent concluded something did not exist. The worst: it ruled that 16 emails were never sent, when they had all gone out days earlier.
- 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.
-
Six New Context Engineering Rules for Claude 5, and the 1,473 Lines I Cut
After reading Anthropic's context engineering guidance for Claude 5, I turned the key points into nine cards, then cut 1,473 lines from a harness I had built up over four model generations.
-
Fewer Prompts Is Not Less Control
Claude 5 and GPT-5.6 official guidance is converging on the same thing — retiring old-style prompt stacking. But trimming is not letting go; control just moves. And the payoff of maintaining that layering is switching tools without losing a step.
-
Two Traps Running Claude Code on Local Ollama: Truncated Context, and A3B Buckling Under Heavy Verification
Two things I logged: cco (Claude Code driven by local Ollama) had long been giving off-topic answers, and the root cause was not a weak model but a full harness whose system prompt had ballooned to 30-50k tokens and was being silently truncated; then I put A3B on the Mac mini for two days as a night worker.
-
A Student's Seven-Agent Setup That Wouldn't Run — A Cautionary Tale About Harness First
A student built seven agents on an M5 Max and kept hitting timeouts. The problem wasn't a weak model — it was skipping the basics: harness, context management, task routing.
-
Two Months of Claude Code Harness Ops: Crashes, Zombies, Cache Misses, and Plan Mode Edges
From March to April, running Claude Code as a long-running harness surfaced a bunch of issues. Survival tactics during the outage, my hook for cleaning up zombie processes, the silent memory bloat fixed in 2.1.86, the resume cache-miss fix in 2.1.90, and the Plan-Mode-question-density problem after 4.7.