Ashlr Brief — Development skill for Claude Code
Toggle response-shortening (caveman-inspired, ashlr-flavored) with three intensity levels.
How to install Ashlr Brief
Installs to ~/.claude/skills/ashlrai-ashlr-plugin-ashlr-brief/SKILL.md
mkdir -p ~/.claude/skills/ashlrai-ashlr-plugin-ashlr-brief && curl -fsSL https://raw.githubusercontent.com/ashlrai/ashlr-plugin/HEAD/commands/ashlr-brief.md -o ~/.claude/skills/ashlrai-ashlr-plugin-ashlr-brief/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Ashlr Brief does
name: ashlr-brief description: Toggle response-shortening (caveman-inspired, ashlr-flavored) with three intensity levels. Trims filler from Claude's prose to save 30–55% on output tokens while keeping code blocks, errors, and destructive-action confirmations in full grammar. argument-hint: "on [lite|standard|concise] | off | status | --project [level]"
Toggle ashlr-brief — a tunable, opt-in response-shortening layer. Free users get user-level preferences; Pro/Team users get project-leve
Alternatives in Development
- Cavemem — Frozen — cross-agent persistent memory for coding assistants 674 ★
- Caveman Claude Skill — Ultra-compressed communication mode for Claude 396 ★
- Contributing To Smart Ralph — "I'm learnding 260 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Caveman Mode
🦴 A Claude skill that makes Claude talk like a caveman. Short sentences. No filler. Just answers.
Claude Short Answer Skill
Initiate with /short - A Claude Code skill that switches output to summary-only mode - cutting reasoning, walk
Tighten Prose
Tighten prose paragraph by paragraph - cut filler, keep facts, add voice
Hewn
Claude Code CLI wrapper: routes every turn to a compact answer shape (IR, prose+code, findings, polished, cave
Ashlr Eco Mode
Toggle eco mode — aggressive token-saving behaviors that trade some response richness for lower session cost.
Toonify MCP
Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, an
Related Agents
Caveman
Rewrites any input into caveman style — terse, blunt, facts only. No greetings, no filler, no explanations. Us
Approval Gate
HumanLayer-inspired approval gate. Enforces human-in-the-loop for HIGH-stakes operations. Classifies actions b
Anti Slop Editor
Audit PR descriptions, commit messages, code comments, and documentation to eliminate AI slop, conversational
