curtis-arch GitHub avatar

Why-Opus-feels-intolerable

curtis-arch

A repository providing tools and reports to study recurring interaction patterns in Claude Code transcripts, focusing on frustration signals and discourse markers, derived from a private three-month corpus.

Stars

6

7-day growth

No data

Forks

0

Open issues

0

License

MIT

Last updated

2026-07-29

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It systematically identifies specific interaction mechanics (e.g., premature certainty, social-repair rituals) that increase cognitive load, offering a reproducible method to improve AI collaboration without vague instructions.

Who it is for

  • Claude Code power users experiencing interaction friction
  • AI interaction researchers studying human-AI communication
  • Prompt engineers seeking evidence-based workspace instructions
  • Developers interested in model behavior analysis at Anthropic or similar

Use cases

  • Analyze your own Claude Code transcripts for frustration episodes
  • Improve Claude workspace instructions to reduce cognitive load
  • Extract and inspect main-agent sessions for qualitative review
  • Validate the analysis pipeline against synthetic fixtures

Strengths

  • Reproducible method with scripts for local corpus analysis
  • Privacy-preserving design: no private data included, pipeline uses local files
  • Practical output: includes recommended instructions derived from findings
  • Thorough analysis of Claude constitution linking training objectives to observed style

Considerations

  • Observational case study from a single operator, not a randomized benchmark
  • Temporal association does not prove causality between response and frustration
  • Results may not generalize to different Claude models or use cases

README quick start

Quick start

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482