bench-check

A performance regression check. It runs benchmark tests, which measure things such as build speed or query latency, and compares the results with a saved baseline.

In plain words
What is it for?
Use it to save a benchmark baseline, compare current results, set a regression threshold, and update the baseline when appropriate.
Why use it?
It helps detect slowdowns that may otherwise go unnoticed between releases or code changes.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/optave/ops-codegraph-tool/bench-check
Any agent
npx skills add optave/ops-codegraph-tool --skill bench-check
Clone the repo
git clone --depth 1 https://github.com/optave/ops-codegraph-tool

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,955 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.02955
Opus 5 $0.00013 $0.01477
Sonnet 5 $0.00005 $0.00591
Haiku 4.5 $0.00003 $0.00296

Measured yesterday against content hash 8b3ffe67208e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bench-check 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 yesterday.

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.

.claude/skills/bench-check/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/bench-check — Performance Regression Check

Run the project's benchmark suite, compare results against a saved baseline, flag regressions beyond a threshold, and optionally update the baseline. Prevents silent performance degradation between releases.

Arguments

  • $ARGUMENTS may contain:
    • --save-baseline — run benchmarks and save as the new baseline (no comparison)
    • --compare-only — compare against baseline without updating it
    • --threshold N — regression threshold percentage (default: 15%)
    • No arguments — compare against baseline, then update it if no regressions

Phase 0 — Pre-flight

  1. Confirm we're in the codegraph repo root
  2. Check that benchmark scripts exist:
    • scripts/benchmark.js (build speed, query latency)
    • scripts/incremental-benchmark.js (incremental build tiers)
    • scripts/query-benchmark.js (query depth scaling)
    • scripts/embedding-benchmark.js (search recall) — optional, skip if embedding deps missing
  3. Parse $ARGUMENTS:
    • SAVE_ONLY=true if --save-baseline
    • COMPARE_ONLY=true if --compare-only
    • THRESHOLD=N from --threshold N (default: 15)
  4. Check for existing baseline at generated/bench-check/baseline.json
    • If missing and not --save-baseline: warn that this will be an initial baseline run

Phase 1 — Run Benchmarks

Run each benchmark script and collect results. Each script outputs JSON to stdout.

1a. Build & Query Benchmark

output=$(timeout 300 node scripts/benchmark.js 2>&1)
exit_code=$?

If exit_code is 124: record "timeout" for this suite and skip to the next suite. Else if exit_code is non-zero: record "error: $output" for this suite and skip to the next suite.

Extract:

  • buildTime (ms) — per engine (native, WASM)
  • queryTime (ms) — per query type
  • nodeCount, edgeCount — graph size

1b. Incremental Benchmark

output=$(timeout 300 node scripts/incremental-benchmark.js 2>&1)
exit_code=$?

If exit_code is 124: record "timeout" for this suite and skip to the next suite. Else if exit_code is non-zero: record "error: $output" for this suite and skip to the next suite.

Read the full file on GitHub · 298 lines

Changes

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.

  1. yesterday First seen · 298 lines · 25 tokens per session scan A 8b3ffe67208e

Subscribe to this mod's changes

bench-check is a skill published in the GitHub repository optave/ops-codegraph-tool (92 stars, last pushed 3d ago), licensed Apache-2.0. It adds 25 tokens to every session and 2,955 once invoked, about $0.0001 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

codespaces

Build and query architecture-aware code search, dependency graphs, call flows, impact analysis, and belief maps for Python, TypeScript, TSX, Rust, C#, Java, Go, Ruby, and Ruby on Rails repositories. Use before non-trivial code changes to find module boundaries, blast radius, architecture violations, and the minimal…

diskd-ai/codespaces · 74 tokens

security-triage

Turn a large codebase into a short, ranked reading list of security-relevant code paths worth a human researcher's time, using the flyto-indexer MCP tools. Use when asked to find, prioritize, or triage potential vulnerabilities / taint flows / attack surface in a repository indexed (or indexable) by flyto-indexer …

flytohub/flyto-indexer · 105 tokens

devlens

Understand a codebase with the DevLens MCP — TypeScript, JavaScript, Python, Go, Rust, or Java (incl. React/Next.js/Node, FastAPI/Flask/Django, Spring Boot, Gin/Echo/chi/net-http, axum/actix/rocket). Query a precomputed graph of nodes (components, hooks, functions, classes, methods, structs, traits, routes) and typed…

devlensio/devlensOSS · 0 tokens

archon

Multi-language dependency impact analysis for Java, JS/TS, and Python codebases. Answers "if I change this, what breaks?" Run /archon diff before refactoring, /archon analyze for full dependency maps.

Schr0d/Archon · 48 tokens

codebase-intelligence

Query the codebase-intelligence CLI to understand TypeScript architecture, dependencies, blast radius, and risk before reading files. Use for any "how is this structured", "what breaks if I change X", "where is the complexity" question.

bntvllnt/codebase-intelligence · 54 tokens

repomix

Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.

yamadashy/repomix · 58 tokens