A chat command that exercises CRUX features through agent interactions and writes the results to a Markdown test report.

Running all CRUX tests or testing only compression, decompression, utilities, or semantic validation, with the report saved as CRUX-TEST-REPORT.md.

It checks whether compression, decompression, utilities, and semantic validation behave as expected, while producing a record of the results.

How zotoio/CRUX-Compress configures Claude Code and Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to zotoio/CRUX-Compress. 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/zotoio/CRUX-Compress/main/.cursor/commands/crux-test.md

Clone the repo

git clone --depth 1 https://github.com/zotoio/CRUX-Compress

Made for: Claude Code, Cursor.

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/zotoio/crux-compress/crux-test/github.svg)](https://agentmods.dev/commands/zotoio/crux-compress/crux-test)

Your own site

<a href="https://agentmods.dev/commands/zotoio/crux-compress/crux-test"><img src="https://agentmods.dev/badge/commands/zotoio/crux-compress/crux-test/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/zotoio/crux-compress/crux-test"><img src="https://agentmods.dev/badge/commands/zotoio/crux-compress/crux-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 328 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00328
Opus 5.5	$0.00000	$0.00131
Sonnet 5.5	$0.00000	$0.00066
Haiku 4.5	$0.00000	$0.00033

Measured 1mo ago against content hash 858063dd9554, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crux-test 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.

.cursor/commands/crux-test.md · 29 lines

What it actually says

crux-test

Run the CRUX command suite via pytest. Test cases live in evals/test_r_crux_command_suite.py; LLM-driven scenarios are marked llm_driven and skipped by default in CI.

Usage

Command	Description
`python3 scripts/run_crux_command_suite.py`	All deterministic tests
`python3 scripts/run_crux_command_suite.py --smoke`	Fast CI smoke subset
`python3 -m pytest evals/test_r_crux_command_suite.py -m crux_command_smoke -v`	Smoke, verbose

Historical Scenario → Pytest Mapping

Historical /crux-test scenario	Pytest class
1 — Compression Test	`TestCompressionRoundtrip`
2 — Decompression Test	`TestDecompressionUnderstanding` (llm_driven)
3 — Token Estimation Test	`TestTokenEstimation`
4 — Checksum Test	`TestChecksumDeterminism`
5 — Install Script Test	`TestInstallScript`
6 — Semantic Validation Test	`TestSemanticValidation` (llm_driven)
7 — Special Characters Test	`TestSpecialCharacters`
8 — Crux-Compress Command Test	`TestCruxCompressWorkflow`
9 — Semantic Stability / Drift Detection	`TestSemanticStabilityDriftDetection`
10 — Force Recompression Test	`TestForceRecompression`

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.

1mo ago Changed · -290 lines 858063dd9554
2mo ago First seen · 319 lines · 0 tokens per session scan A 8eafe26f5998

Subscribe to this mod's changes

crux-test is a command published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 328 tokens. 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.

Testing claude compression cursor markdown optimisation rules

crux-test next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
crux-testzotoio/CRUX-Compress	Command	8	14d ago	MIT	A	0	Claude Code, Cursor
convertojspace/md-anything	Command	49	yesterday	MIT	A	11	Claude Code
doctorojspace/md-anything	Command	49	yesterday	MIT	A	9	Claude Code
ingestojspace/md-anything	Command	49	yesterday	MIT	A	11	Claude Code
a11y-handoffsaralobo/rules-accessibility-handoff	Command	11	8mo ago	none	A	36	Claude Code
initfcakyon/claude-codex-settings	Command	1.2k	yesterday	Apache-2.0	A	0	Claude Code
constraintsvinvcn/addyosmani-agent-skills-zh	Command	46	17d ago	MIT	A	20	Claude Code

CRUX-Compress: Command for Claude Code