Ashlr Benchmark — Development skill for Claude Code
Run the ashlr-plugin token-savings benchmark against the current project.
How to install Ashlr Benchmark
Installs to ~/.claude/skills/ashlrai-ashlr-plugin-ashlr-benchmark/SKILL.md
mkdir -p ~/.claude/skills/ashlrai-ashlr-plugin-ashlr-benchmark && curl -fsSL https://raw.githubusercontent.com/ashlrai/ashlr-plugin/HEAD/commands/ashlr-benchmark.md -o ~/.claude/skills/ashlrai-ashlr-plugin-ashlr-benchmark/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Ashlr Benchmark does
Run the ashlr-plugin token-savings benchmark against the current project.
Alternatives in Development
- Evo — turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then run 1.4k ★
- Aqe Benchmark 325 ★
- Memstack Headroom — Check Headroom proxy status and token savings 294 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Ashlr Dashboard
Rich token-savings dashboard — per-tool bar charts, 7d/30d sparklines, projected annual savings, and cost in d
Warden Bench
Run the golden benchmark suite for one token-warden agent (or all) and compare results against the frozen run1
Bench Login
Authenticate the current Claude Code session with BenchAGI so agents know whose canon, inbox, and instance to
Ashlr Eco Mode
Toggle eco mode — aggressive token-saving behaviors that trade some response richness for lower session cost.
Ashlr Core Efficiency
Token-efficiency primitives for Claude Code: genome, compression, provider-aware budgeting.
Token Saver Stats
Show token-saver compression statistics and savings
Related Agents
Spot Checker
Verifies claims against live remote data — current repository statistics, security advisories, deprecation not
Ashlr Code
Main AshlrCode agent — token-efficient coding, editing, search. Delegates aggressively to ashlr:explore and as
Doc Consistency Reviewer
Audit plugin README parity, platform-specific benchmark evidence and community documentation against Foundry's