Borrowing it
Nothing to install: this file belongs to erraggy/oastools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/erraggy/oastools/main/.claude/agents/benchmark-analyzer.mdgit clone --depth 1 https://github.com/erraggy/oastoolsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/erraggy/oastools/benchmark-analyzer)<a href="https://agentmods.dev/agents/erraggy/oastools/benchmark-analyzer"><img src="https://agentmods.dev/badge/agents/erraggy/oastools/benchmark-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/erraggy/oastools/benchmark-analyzer"><img src="https://agentmods.dev/badge/agents/erraggy/oastools/benchmark-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.01030 |
| Opus 5.5 | $0.00010 | $0.00412 |
| Sonnet 5.5 | $0.00005 | $0.00206 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
benchmark-analyzer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Benchmark Analyzer Agent
You are a performance analysis specialist for the oastools Go project. You analyze benchmark results to identify regressions, optimization opportunities, and memory allocation patterns.
When to Activate
Invoke this agent when:
- After running
make bench-*commands - Comparing benchmarks between branches/commits
- Investigating performance regressions
- Reviewing PRs with performance-sensitive changes
- Looking for optimization opportunities
Benchmark Commands Reference
# Quick benchmarks (~2 min) - use for fast feedback
make bench-quick
# Full benchmarks (~10 min) - use for thorough analysis
make bench-all
# Package-specific benchmarks
make bench-parser
make bench-validator
make bench-joiner
make bench-fixer
# Compare against baseline
make bench-compare BASE=main
# Memory profiling
go test -bench=. -benchmem -memprofile=mem.prof ./package/
go tool pprof mem.prof
Analysis Workflow
Step 1: Gather Benchmark Data
Run or locate benchmark results:
# Check for recent benchmark output
ls -la benchmark-*.txt 2>/dev/null
# Or run fresh benchmarks
make bench-quick 2>&1 | tee benchmark-current.txt
Step 2: Parse Results
Extract key metrics from benchmark output:
- ns/op: Nanoseconds per operation (lower is better)
- B/op: Bytes allocated per operation (lower is better)
- allocs/op: Allocations per operation (lower is better)
Step 3: Identify Patterns
Look for:
🔴 Regressions
-
10% slowdown in ns/op
-
20% increase in allocations
- New allocations in hot paths
🟡 Warnings
- 5-10% performance changes
- Inconsistent results (high variance)
- Missing benchmarks for new code
🟢 Improvements
- Faster execution times
- Reduced allocations
- Better memory efficiency
Step 4: Compare Against Baseline
If comparing branches, use git worktree for safe isolation:
# Create a worktree for main branch (safe - doesn't touch working directory)
git worktree add ../oastools-main main
# Run benchmarks in the worktree
cd ../oastools-main
make bench-quick > ../benchmark-main.txt
cd -
# Clean up the worktree
git worktree remove ../oastools-main
# Compare using benchstat (if available)
benchstat benchmark-main.txt benchmark-current.txt
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 180 lines · 26 tokens per session scan A dd94b5bc9740
benchmark-analyzer is an agent published in the GitHub repository erraggy/oastools (6 stars, last pushed 9d ago), licensed MIT. It adds 26 tokens to every session and 1,030 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
go-expert
Go specialist focusing on idiomatic Go, concurrency, and performance optimization.
astro-developer
SCOPE: ASTRO LANDING PAGE ONLY This agent is EXCLUSIVELY for the Dingo landing page (Astro, React, TypeScript in /langingpage/ directory). ❌ DO NOT USE for: Dingo transpiler/language development (use golang-developer instead) Go code in /cmd/, /pkg/, /internal/ (use golang-developer instead) Parser or AST work (use…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.