oxygen: Instructions file for Claude Code

CLAUDE.md

oxygen CLAUDE.md is an instructions file for Claude Code from oxy-hq/oxygen. It costs 6,200 tokens per session, scanned A, original, Apache-2.0.

A CLAUDE.md instruction file containing project rules for Claude Code, including the Oxy repository layout, build and test guidance, and browser testing notes.

In plain words
What is it for?
It helps the assistant locate services and crates, follow package-manager conventions, run tests, and use Playwright when checking the running app.
Why use it?
It gives the coding assistant the project context and conventions needed to work in a Rust backend and React, TypeScript, and Vite frontend.

Instructions file for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; positional $N argument.

This is oxy-hq/oxygen's own configuration. It tells Claude Code how to work on oxygen 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 oxygen configures →

Reuse

Borrowing it

Nothing to install: this file belongs to oxy-hq/oxygen. 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/oxy-hq/oxygen/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/oxy-hq/oxygen

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 oxygen CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/oxy-hq/oxygen/claude-md/github.svg)](https://agentmods.dev/instructions/oxy-hq/oxygen/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/oxy-hq/oxygen/claude-md"><img src="https://agentmods.dev/badge/instructions/oxy-hq/oxygen/claude-md/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 oxygen CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/oxy-hq/oxygen/claude-md"><img src="https://agentmods.dev/badge/instructions/oxy-hq/oxygen/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,200 This file is loaded in full into every session.
When invoked 6,200 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.06200 $0.06200
Opus 5.5 $0.02480 $0.02480
Sonnet 5.5 $0.01240 $0.01240
Haiku 4.5 $0.00620 $0.00620

Measured yesterday against content hash ac2087a32030, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oxygen CLAUDE.md scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl** when you need real data out of dev/staging/prod, and instead of guessing
CLAUDE.md · 371 lines

How it starts

The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Assistant Guidelines

Injected into every API call, together with product-context.md and internal-docs/backend-architecture.md (both @-imported below). State each rule once, in the section that owns it. A recap section is how three copies of the --local rule accumulated here; if a rule feels worth repeating, the first statement is the one to sharpen. Anything retrievable by reading the code in a minute belongs in the code or a crate-local CLAUDE.md, not here.

Oxy (brand: Oxygen) is a Rust workspace + web frontend. The oxy CLI/server binary lives in the server crate (oxy-server, the default workspace member) — a thin composition root that mounts API surfaces over the app crate (oxy-app), the CLI + HTTP-server library where almost all the code lives.

  • Rust · async Tokio · ORM Sea-ORM (PostgreSQL) · HTTP Axum
  • Frontend Vite + React + TypeScript, pnpm (never npm/yarn)

Workspace Layout

crates/
  server/                   # (oxy-server) the `oxy` BINARY — composition root (main.rs + router
                            #   assembly) that mounts the API surfaces. Default member.
  app/                      # (oxy-app) CLI + HTTP server LIBRARY (the bulk of the code; lib-only)
  api-<context>/            # (oxy-api-*) HTTP surface crates oxy-server mounts — one bounded context
                            #   each; oxy-app does NOT depend on them. Placement rules S1–S7 and the
                            #   per-crate review: internal-docs/domain-boundaries.md
  route-catalog/             # (oxy-route-catalog) generated GET /api/_catalog table; sits ABOVE oxy-app
                            #   so a surface edit doesn't rebuild oxy-app. oxy-server hands it in
  app-dylib/                # (oxy-app-dylib) dev-only dynamic-linking shim, EXCLUDED from the
                            #   workspace; built only by `--features dev-dynamic` (just dev-backend-dyn)
  app-core/                 # (oxy-app-core) Shared app-layer seam: audit, serve_mode,
                            #   org/custom-app subdomain dispatch, member authz
  tenancy/                  # (oxy-tenancy) Tenancy domain logic shared across contexts: org teams +
                            #   app-access grants. Below oxy-app and the api-* surfaces; no routes
  core/                     # (oxy) Core platform library, published as "oxy"
  auth/                     # (oxy-auth) Authentication — who you are
  authz/                    # (oxy-authz) Authorization — what you may do. THE authority model
  entity/  migration/       # Sea-ORM entities / migrations
  semantic/                 # (oxy-semantic) Semantic query layer (airlayer)
  shared/                   # (oxy-shared) Shared types, errors, infra
  project/                  # (oxy-project) Project/model config domain
  oxy-compile/              # (oxy-compile) Compile boundary: workspace FS → Postgres rows
  workspace-fs/             # (oxy-workspace-fs) Workspace filesystem helpers (thin)
  git/                      # (oxy-git) Git client / worktree ops
  platform/                 # (oxy-platform) Platform services
  billing/                  # (oxy-billing) Stripe billing
  metric-monitoring/        # (oxy-metric-monitoring) Anomaly monitors / metric tree
  observability/            # (oxy-observability) Customer-facing observability backend
  telemetry/                # (oxy-telemetry) Platform telemetry: OTLP traces+logs → cluster OTel
                            #   collector (ClickStack/HyperDX), stderr JSON format, HTTP request spans
  airform/                  # (oxy-airform) dbt-style modeling
  airhouse/                 # (airhouse) Warehouse + connector
  cameras/                  # (oxy-cameras) Camera fleet domain
  test-utils/               # (oxy-test-utils) Fixtures & mocks
  agentic/
    core/ runtime/ pipeline/ analytics/ builder/ automation/ airway/
    connector/ http/ llm/ semantic/    # see crates/agentic/CLAUDE.md for layering
  infrastructure/llm/oxy-llm
  infrastructure/semantic/  # (oxy-airlayer-compat) airlayer compatibility shim
  integration/{looker,unifi,omni}
web-app/                    # Frontend (see web-app/CLAUDE.md)
sdk/cli/                    # (@oxy-hq/cli) the `oxyc` CLI — the gh-api-style client for
                            #   the HTTP API, plus the customer-account tooling. TypeScript,
                            #   NOT Rust: it replaced `oxy api`, which was deleted from
                            #   crates/app. See internal-docs/oxy-api-cli.md
sdk/cli/skills/             # THE Oxy platform skills — published to oxy-hq/skills and installed
                            #   by customers' agents. Update one in the PR that changes the
                            #   behaviour it describes. internal-docs/platform-skills.md

Read the full file on GitHub · 371 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. yesterday Changed · +10 lines · +205 tokens per session ac2087a32030
  2. 2d ago First seen · 361 lines · 5,995 tokens per session scan A 4d9926aabe12

Subscribe to this mod's changes

oxygen CLAUDE.md is an instructions file published in the GitHub repository oxy-hq/oxygen (203 stars, last pushed yesterday), licensed Apache-2.0. It adds 6,200 tokens to every session, about $0.0248 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.

Related

Other instructions, from other repositories

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 · 9,649 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 · 7,257 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,159 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens