agentsclimarketplace

Stale persistent context detection

Skill kjuhwa/skills-hub/skills/workflow/stale-persistent-context-detection

Self-correcting knowledge corpus for Claude Code — 9 stable shape clusters, bias-correction pipeline baked into contribution flow. 47 papers, 45 techniques, 1.1k skills.

Install
npx -y skills add kjuhwa/skills-hub --skill stale-persistent-context-detection

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Detect and remove stale error snapshots that LLM tools inject via persistent-context files (CLAUDE.md, AGENTS.md, system prompts, memory) before chasing a fix. If the current source already compiles, the injected error is a ghost from a previous session, not a real bug.

SKILL.md

0.8 KB, 25 tokens by cl100k_base, as published. Nobody here has run it

Stale Persistent-Context Detection

See content.md for the detection protocol, false-positive guards, and cleanup steps.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.