dani-lore

Context Audit — Security skill for Claude Code

Security community

Audit how much input-token bloat the read-guard removes on this repo.

How to install Context Audit

Installs to ~/.claude/skills/dani-lore-token-economy-kit-context-audit/SKILL.md

Terminal

mkdir -p ~/.claude/skills/dani-lore-token-economy-kit-context-audit && curl -fsSL https://raw.githubusercontent.com/dani-lore/token-economy-kit/HEAD/commands/context-audit.md -o ~/.claude/skills/dani-lore-token-economy-kit-context-audit/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Context Audit does

description: Audit how much input-token bloat the read-guard removes on this repo allowed-tools: Bash(node "${CLAUDE_PLUGIN_ROOT}/benchmarks/score.mjs") disable-model-invocation: true

Report the input-bloat benchmark for the current working directory: the tokens an agent would spend on blind Reads here, and how much the read-guard cuts.

Scorer output:

!`node "${CLAUDE_PLUGIN_ROOT}/benchmarks/score.mjs"`

From that output, report in at most six lines:

the cut ratio (baseline vs guard

Alternatives in Security

Security Guardian — Comprehensive security analysis for RTK CLI tool, focusing on command injection, shell escaping, hook security 11.9k ★
Octoboss Clean Contexts — You are the Octoboss — a cross-tentacle orchestrator 1.4k ★
Imcodes — The IM for agents 960 ★