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.
npx agentmods add instructions/nguyenyou/scalex/claude-mdgit clone --depth 1 https://github.com/nguyenyou/scalexWrote 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/instructions/nguyenyou/scalex/claude-md)<a href="https://agentmods.dev/instructions/nguyenyou/scalex/claude-md"><img src="https://agentmods.dev/badge/instructions/nguyenyou/scalex/claude-md.svg" alt="Measured on agentmods" 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 | $0.03084 | $0.03084 |
| Opus 5 | $0.01542 | $0.01542 |
| Sonnet 5 | $0.00617 | $0.00617 |
| Haiku 4.5 | $0.00308 | $0.00308 |
Grade A, and why
scalex CLAUDE.md 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 5d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What is Scalex
Scalex is a Scala code intelligence CLI for coding agents. It provides fast symbol search, find definitions, and find references — without requiring an IDE, build server, or compilation. Designed as a Claude Code plugin.
IMPORTANT: No company references
NEVER mention any company names, internal project names, proprietary codebases, or organization-specific details in any output — including commit messages, PR descriptions, changelogs, roadmaps, documentation, code comments, or conversations. Always use generic examples (e.g. HttpMessageService, UserServiceLive) instead.
Search scope
Source code lives in src/ (scalex production code), clibase/src/ (CLI base module), graph/src/ (asciiGraph module), and tests/ (test suite). When searching for Scala code, scope searches to these directories. Avoid searching repo-wide — benchmark/ contains ~17.7k Scala files from the scala3 compiler clone that will pollute results.
Workflow
- Before planning or implementing any feature, first add it to
docs/ROADMAP.mdunder the appropriate section - The roadmap is the source of truth for what's planned and what's done
- Bug fix workflow: When receiving a bug report, always write a failing test that reproduces the bug before writing the fix. This validates the bug is real and ensures the fix is verifiable. Only then apply the code fix and confirm the test passes.
Build & Run
# Run via Mill (development)
./mill run <command> [args...]
# Run tests
./mill test
# Run microbenchmarks
./mill bench.run <benchmark> <workspace> [options]
# Build GraalVM native image (requires GraalVM)
./build-native.sh
# Output: ./scalex (~41MB standalone binary)
# Validate Claude Code plugin structure
claude plugin validate plugins/scalex/
Architecture
Source code is in src/ (scalex), clibase/src/ and graph/src/ (library modules), tests in tests/ (Scala 3.8.3, JDK 21+). When searching the codebase, scope to these directories to avoid hitting benchmark data or build artifacts.
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.
- 5d ago First seen · 182 lines · 3,084 tokens per session scan A 6c8273681441
scalex CLAUDE.md is an instructions file published in the GitHub repository nguyenyou/scalex (95 stars, last pushed 2mo ago), licensed MIT. It adds 3,084 tokens to every session, about $0.0154 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.
Other instructions, from other repositories
roam-code AGENTS.md
AGENTS.md instructions for Cranot/roam-code, covering agents.md — roam-code development guide, what this project is, documentation hub, where files go (private vs public) and quality discipline (from internal/dogfood/ + agi-in-md).
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
trace-mcp CLAUDE.md
Claude Code instructions for nikolai-vysotskyi/trace-mcp, covering trace-mcp development guide, what this project is, agent behavior — read before every task, no flattery, no filler and disagree when the premise is wrong.
supi CLAUDE.md
Claude Code instructions for mrclrchtr/supi, covering claude.md, development status, pi docs-first rule, documentation expectations and package layout convention.
trace-mcp AGENTS.md
AGENTS.md instructions for nikolai-vysotskyi/trace-mcp: IMPORTANT: For ANY code exploration task, ALWAYS use trace tools first. NEVER use Read/Grep/Glob/Bash(ls,find) for navigating source code.
sourcebot CLAUDE.md
Claude Code instructions for sourcebot-dev/sourcebot, covering claude code guidelines, database migrations, building packages, backend workloads and execution locks.