runx CLAUDE.md

runx CLAUDE.md is an instructions file for coding agents from runxhq/runx. It costs 792 tokens per session, scanned A, original, Apache-2.0.

Instructions for working on the runx software project, including its architecture, development commands, release practices, and specification workflow. It defines which parts of the system own contracts, parsing, execution, and other responsibilities.

In plain words
What is it for?
Use it when implementing or reviewing runx changes, following a scafld specification, checking the Rust and TypeScript parts, or running the project's type, dependency-graph, and verification commands.
Why use it?
It helps contributors follow the project's boundaries and avoid duplicating trusted behavior in the wrong language or package. It also points to focused checks for validating changes.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/runxhq/runx/claude-md
Clone the repo
git clone --depth 1 https://github.com/runxhq/runx

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 runx CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/runxhq/runx/claude-md.svg)](https://agentmods.dev/instructions/runxhq/runx/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/runxhq/runx/claude-md"><img src="https://agentmods.dev/badge/instructions/runxhq/runx/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 792 This file is loaded in full into every session.
When invoked 792 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00792 $0.00792
Opus 5 $0.00396 $0.00396
Sonnet 5 $0.00158 $0.00158
Haiku 4.5 $0.00079 $0.00079

Measured 5d ago against content hash b1f78f54613c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runx 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.

CLAUDE.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

runx OSS Claude Contract

Read AGENTS.md first when working through a scafld spec. For direct code cleanup, follow this file plus CONVENTIONS.md.

Architecture

Rust owns the trusted local runtime path:

  • runx-contracts owns public contract types and schema emission.
  • runx-core owns pure state-machine and policy decisions.
  • runx-parser owns pure skill, graph, runner, and tool manifest parsing.
  • runx-receipts owns canonical receipt hashing, signatures, and tree proof.
  • runx-runtime owns impure local execution, adapters, process invocation and supervision, harness replay, journals, registry clients, payment gates, MCP, and receipts.
  • runx-cli is the native command shell over runx-runtime.

TypeScript packages are generated contract validators/types, distribution and client wrappers, language-neutral extension helpers, host adapters, and product integration glue. Skill authoring belongs to the native authoring service and Skill Lab. TypeScript must not regain a second authoring path or trusted local execution fallback behavior.

Commands

Use the narrowest useful check while iterating:

pnpm typecheck
pnpm rust:crate-graph
pnpm verify:fast

For Rust-focused checks:

cargo fmt --manifest-path crates/Cargo.toml --all --check
cargo check --manifest-path crates/Cargo.toml --workspace --all-targets
cargo test --manifest-path crates/Cargo.toml -p runx-receipts

Avoid running multiple heavy Rust gates in parallel; this workspace has had false timeouts when the eval binary is starved.

Release Discipline

cli-vX.Y.Z is the CLI distribution version only. It may stamp/publish packages/cli, native npm packages, and the runx-cli crate. It must not stamp or publish internal Rust library crates unless the operator explicitly requests a separate library-crate release.

Do not bump another patch to fix a broken release channel. Repair the existing release asset, channel manifest, or workflow in place, and validate the manifest against the actual archive contents before claiming the channel is live.

Read the full file on GitHub · 91 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. 5d ago First seen · 91 lines · 792 tokens per session scan A b1f78f54613c

Subscribe to this mod's changes

runx CLAUDE.md is an instructions file published in the GitHub repository runxhq/runx (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 792 tokens to every session, about $0.0040 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.