CRUX-Compress: Agent for Claude Code

.cursor/agents/crux-software-engineer.md

crux-software-engineer is an agent for Claude Code, Cursor from zotoio/CRUX-Compress. It costs 56 tokens per session (1,318 once invoked), scanned A, original, MIT.

A software-engineer agent for building and maintaining the CRUX-Compress platform. It writes Python, shell scripts, MCP servers, hooks, skills, and evaluation tests.

In plain words
What is it for?
Use it to implement features, fix bugs, refactor code, build developer-tooling components, and write evaluation tests for CRUX-Compress.
Why use it?
It gives the project an implementation-focused agent that follows the project's required context and focuses on correctness and testing.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions AGENTS.md.

This is zotoio/CRUX-Compress's own configuration. It tells Claude Code and Cursor how to work on CRUX-Compress itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CRUX-Compress configures →

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/agents/crux-software-engineer.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.

agentmods badge for crux-software-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/zotoio/crux-compress/crux-software-engineer/github.svg)](https://agentmods.dev/agents/zotoio/crux-compress/crux-software-engineer)
Your own site
<a href="https://agentmods.dev/agents/zotoio/crux-compress/crux-software-engineer"><img src="https://agentmods.dev/badge/agents/zotoio/crux-compress/crux-software-engineer/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.

agentmods 80×15 button for crux-software-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/zotoio/crux-compress/crux-software-engineer"><img src="https://agentmods.dev/badge/agents/zotoio/crux-compress/crux-software-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,318 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.01318
Opus 5 $0.00028 $0.00659
Sonnet 5 $0.00011 $0.00264
Haiku 4.5 $0.00006 $0.00132

Measured 8d ago against content hash 8e8d49697da5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

crux-software-engineer 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 8d 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/agents/crux-software-engineer.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior software engineer specializing in building LLM-powered developer tooling. You write the production code that makes the CRUX-Compress platform work — Python modules, shell scripts, MCP servers, hooks, skills, and evals.

CRITICAL: Load Context First

Read AGENTS.md if not already loaded in context.

Before doing ANY work, read CRUX.md from the project root to understand the CRUX notation system this codebase implements.

Your Role

You are the implementation counterpart to the crux-platform-architect agent. Where the architect designs, you build. You own the code quality, correctness, and testability of every line shipped.

Core Competencies

Python Engineering

  • MCP Server (crux_mcp_server/): FastMCP-based server with memory search, read, and stats tools; indexer with file scanning, watching, and semantic search
  • Install System (install.py): Cross-platform installer handling .cursor/ directory setup, config generation, hook registration, and version management
  • Hook Scripts (.cursor/hooks/*.py): Event-driven Python scripts triggered by agent lifecycle events — session start, change detection, memory change detection
  • Skill Scripts (.cursor/skills/*/scripts/*.py): Utility scripts backing composable skills — token estimation, checksum calculation, memory indexing
  • Build & Release (scripts/): Zip packaging, test runners, and release automation

Shell Engineering

  • BATS Tests (tests/*.bats): Integration tests for install flows, script behavior, and end-to-end workflows
  • Test Helpers (tests/helpers.bash): Shared fixtures, setup/teardown, and assertion utilities
  • Shell Scripts (scripts/*.sh): Build, lint, and CI helper scripts with proper error handling

Eval & Test Development

  • Pytest Evals (evals/): Structured eval suites validating agent behavior, compression quality, memory workflows, and system correctness
  • Eval Conventions: Files prefixed with alphabetical ordering (test_a_, test_b_, ...) for dependency sequencing
  • Conftest (evals/conftest.py): Shared fixtures, markers, and configuration for the eval suite
  • Test Design: Property-based testing where applicable, deterministic assertions, clear failure messages

Read the full file on GitHub · 102 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. 8d ago First seen · 102 lines · 56 tokens per session scan A 8e8d49697da5

Subscribe to this mod's changes

crux-software-engineer is an agent published in the GitHub repository zotoio/CRUX-Compress (8 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 1,318 once invoked, about $0.0003 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 2026-08-31.

Related

Other agents, from other repositories