What is benchmark-compare?

A command that compares benchmark results on the current working tree with a reference revision. A benchmark measures performance or behavior under a defined test setup.

Use it to compare the current code with a revision such as origin/main and record results when the required clean-tree conditions are met.

It shows per-test changes and pass or fail results instead of hiding differences in one total.

How jgravelle/jcodemunch-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jgravelle/jcodemunch-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jgravelle/jcodemunch-mcp/main/.claude/commands/benchmark-compare.md

Clone the repo

git clone --depth 1 https://github.com/jgravelle/jcodemunch-mcp

Made for: Claude Code.

Or install jcodemunch, the plugin that ships this one along with the rest of its 10 skills, 7 commands, 2 agents, 2 hooks, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jgravelle/jcodemunch-mcp/benchmark-compare.svg)](https://agentmods.dev/commands/jgravelle/jcodemunch-mcp/benchmark-compare)

Your own site

<a href="https://agentmods.dev/commands/jgravelle/jcodemunch-mcp/benchmark-compare"><img src="https://agentmods.dev/badge/commands/jgravelle/jcodemunch-mcp/benchmark-compare.svg" alt="Measured on agentmods" height="20"></a>

Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,213 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin unknown 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.

Model	Per session	Once invoked
Fable 5.1	$0.00070	$0.01213
Opus 5	$0.00035	$0.00607
Sonnet 5	$0.00014	$0.00243
Haiku 4.5	$0.00007	$0.00121

Measured 3d ago against content hash 148e57fb4351, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

benchmark-compare scanned grade B with 1 finding 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

the same bench command ⚠ After ANY `uv sync` in a worktree, check the six jcodemunch hook paths in `~/.claude/settings.json` still point at this checkout's `.venv` (W-34: a worktree sync re-registered them to the worktre

.claude/commands/benchmark-compare.md · 71 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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.

3d ago First seen · 71 lines · 70 tokens per session scan B 148e57fb4351

Subscribe to this mod's changes

benchmark-compare is a command published in the GitHub repository jgravelle/jcodemunch-mcp (2,672 stars, last pushed today), with no licence file. It adds 70 tokens to every session and 1,213 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Analytics and metrics Claude Code Testing ai-coding ast claude code-intelligence context-window

coverage

Ingest or inspect test-coverage reports — LCOV, Cobertura/Clover, or coverage.py .coverage (builds the per-test map when contexts are present).

repowise-dev/repowise · 34 tokens

test-suite

Run comprehensive test suite with coverage analysis.

travisjneuman/.claude · 7 tokens

bucle

Lanzar bucle autónomo para ejecutar historias del PRD.

doncheli/don-cheli-sdd · 13 tokens

avance-rapido

Crear todos los artefactos de planificación de un golpe (fast-forward).

doncheli/don-cheli-sdd · 15 tokens

testloop

Role: Autonomous quality enforcement engine. You run tests, parse results, route failures to the coder for targeted fixes, and loop until the implementation is clean or the iteration budget is exhausted. You never accept "it should work" — only green tests.

samibs/skillfoundry · 0 tokens

test-map

/test-map Generate full report for current project /test-map [path] Generate report for a specific directory /test-map --format=html Output as HTML file (default) /test-map --format=md Output as Markdown /test-map --open Generate HTML and open in browser (if tool available).