Context Gardening — Security skill for Claude Code
Audit CLAUDE.md, its linked docs, and .claude/memory/ against the patterns from "A good AGENTS.md is a model upgrade" — flag bloat, stale references, mis-fit patterns, and verbose passages, then apply.
How to install Context Gardening
Installs to ~/.claude/commands/frankray78-netpace-context-gardening.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/FrankRay78/NetPace/HEAD/.claude/commands/context-gardening.md -o ~/.claude/commands/frankray78-netpace-context-gardening.md Restart Claude Code, or start a new session, for it to be picked up.
What Context Gardening does
description: Audit CLAUDE.md, its linked docs, and .claude/memory/ against the patterns from "A good AGENTS.md is a model upgrade" — flag bloat, stale references, mis-fit patterns, and verbose passages, then apply approved edits. reference: https://www.augmentcode.com/blog/how-to-write-good-agents-dot-md-files
Run this command quarterly, after a big architectural shift, or whenever `CLAUDE.md` feels stale. It treats `CLAUDE.md` + the docs it links to + `.claude/memory/` as a garden to p
Alternatives in Security
- Imcodes — The IM for agents 960 ★
- Data Viz Audit — Audit a data visualization for chart type selection, accessible color palette, annotations, and anti-patterns 309 ★
- Memory Self Review — Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMOR 297 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Audit Claude Components
Comprehensive audit of .claude folder. Checks structure, quality, cross-references, antipatterns, resource usa
Audit Docs
Scan documentation for staleness — broken links, outdated counts, stale version references, and inconsistencie
Memory Checkup
Audit and repair an AI agent's memory corpus for consistency: stale numbers, dangling references, dead daily f
Gaia Audit
Audit memory, wiki, and auto-loaded files for duplication, conflicting instructions, and stale content. The de
Hub Audit
Monthly adversarial self-audit of the hub — a fresh, context-free worker hunts for drift, stale rules, and sel
Tidy Context
Audit and prune CLAUDE.md / nested CLAUDE.md / project memory files — verify claims against the repo, remove s
Related Agents
Paper Density
Review academic papers for information density. Finds redundancy, repeated data, duplicate presentations (tabl
Doc Consistency Reviewer
Audit plugin README parity, platform-specific benchmark evidence and community documentation against Foundry's
Review Comments
Aggressively reviews inline code comments in the diff — flags comments that are unnecessary, redundant, stale,