ummon: Instructions file for Claude Code

CLAUDE.md

ummon CLAUDE.md is an instructions file for Claude Code from Nayshins/ummon. It costs 926 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for developing the Ummon Rust project, including commands for building, running, testing, formatting, and checking code quality.

In plain words
What is it for?
Use them when modifying Ummon, especially to build or run it, index or query a directory, run tests, format Rust code, or check Clippy warnings.
Why use it?
They give the coding agent the project's expected workflow and testing rules, reducing mistakes such as committing unformatted code or changing correct tests to hide failures.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Nayshins/ummon's own configuration. It tells Claude Code how to work on ummon 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 ummon configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Nayshins/ummon. 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/Nayshins/ummon/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Nayshins/ummon

Made for: Claude Code.

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 ummon CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nayshins/ummon/claude-md.svg)](https://agentmods.dev/instructions/nayshins/ummon/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nayshins/ummon/claude-md"><img src="https://agentmods.dev/badge/instructions/nayshins/ummon/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 926 This file is loaded in full into every session.
When invoked 926 The same file — it is already loaded in full.
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 $0.00926 $0.00926
Opus 5 $0.00463 $0.00463
Sonnet 5 $0.00185 $0.00185
Haiku 4.5 $0.00093 $0.00093

Measured 7d ago against content hash 3f64efc698c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ummon 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 7d 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.

CLAUDE.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ummon Development Guide

IMPORTANT Make sure to follow these rules when writing code in this repository

Build & Test Commands

# Build the project
cargo build

# Run the project
cargo run

# Run with specific command
cargo run -- index .      # Index current directory
cargo run -- query "show funcs"  # Query the knowledge graph

# Run tests
cargo test
cargo test -- --nocapture  # Show test output
cargo test <test_name>     # Run specific test

# Format code
cargo fmt

Pre-Commit Checklist

  • ALWAYS run cargo fmt before committing code
  • Run cargo clippy to check for code improvements
  • ALWAYS fix any Clippy warnings before committing
  • Ensure all tests pass with cargo test

Test Structure

Tests have been set up as inline modules within each source file using Rust's #[cfg(test)] attribute.

Test Principles

  • CRITICAL: When a test fails, NEVER change the test assertions to match incorrect implementation. Always:
    1. Verify that the test assertions represent the correct expected behavior
    2. If the test is correct, fix the implementation to match the expected behavior
    3. Only modify test assertions if the test itself is incorrect (not to match buggy code)
  • Tests should be independent and not rely on external state or environment variables
  • Mock external dependencies rather than making real API calls
  • Each test should focus on a specific behavior or feature

Code Style Guidelines

  • Imports: Group standard library imports first, followed by external crates, then local modules
  • Error Handling: Use anyhow::Result for functions that can fail, with ? operator for propagation
  • Naming: Use snake_case for variables and functions, CamelCase for types
  • Types: Prefer strong typing with descriptive type names
  • Documentation: Include doc comments for public API functions
  • Formatting: Follow Rust style guidelines with 4-space indentation
  • Modules: Organize code in modules by functionality (parser, graph, commands)
  • Warnings: Do not check in new warnings
  • Dead Code: Eliminate unused functions, variables, and imports. There are no backward compatibility requirements at this time.
  • Error Handling Pattern: Use Result types with context for error handling rather than unwrapping. Prefer map_or over unwrap_or patterns.
  • Functional Style: Prefer functional chains with methods like filter, map, and and_then over deeply nested if-let statements. Example:
    // Prefer this:
    let result = some_option
        .filter(|x| condition(x))
        .and_then(|x| transform(x))
        .map(|x| x.to_string());
        
    // Over this:
    let mut result = None;
    if let Some(x) = some_option {
        if condition(x) {
            if let Some(y) = transform(x) {
                result = Some(y.to_string());
            }
        }
    }
    
  • Code Completion: Always complete implementation for all code paths. Do not add placeholder code or TODO comments unless specifically instructed to. Complete all functionality according to requirements before committing code.

Read the full file on GitHub · 87 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. 7d ago First seen · 87 lines · 926 tokens per session scan A 3f64efc698c8

Subscribe to this mod's changes

ummon CLAUDE.md is an instructions file published in the GitHub repository Nayshins/ummon (38 stars, last pushed 1y ago), licensed Apache-2.0. It adds 926 tokens to every session, about $0.0046 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 instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens