Command-output safety net for coding agents: keep known CLI noise out with deterministic filters, conservative passthrough, and --raw.
Local-first context hygiene for AI coding agents — Claude Code plugin plus shell helpers for large reads, noisy output, redaction, artifacts, and measured token/cost evidence.
Context hygiene for agentic coding. Save and resume Claude Code/Codex sessions.
Local-first context hygiene tooling for AI coding sessions
Context hygiene & risk adjudication for LLM pipelines: secrets, PII, prompt-injection, policy redaction & tokenization.
Skill-first context hygiene toolkit for AI agents
A small protocol for keeping AI coding assistants honest — one AI session does the work and declares claims, a separate session verifies them, a human approves.
Thin authority overlay for mapping trust, scope, and freshness across AI coding-agent context systems.
opencode custom tool: run long Python/Shell scripts with stdout/stderr redirected to disk + PowerShell watchdog freeze-kill. Context hygiene for tqdm/akshare/PDF-heavy scripts. MIT.
Add a description, image, and links to the context-hygiene topic page so that developers can more easily learn about it.
To associate your repository with the context-hygiene topic, visit your repo's landing page and select "manage topics."