Conduit: Instructions file for Claude Code

CLAUDE.md

Conduit CLAUDE.md is an instructions file for Claude Code from nickna/Conduit. It costs 4,838 tokens per session, scanned A, original, MIT.

A repository instruction guide for Claude Code, the coding assistant, explaining which development commands are safe and which can damage the project environment.

In plain words
What is it for?
Following project-specific startup rules, checking WebAdmin changes with linting and type checks, and avoiding forbidden build or Docker commands.
Why use it?
It prevents the assistant from running commands that corrupt the development container or require a long restart. It also gives safer checks for validating changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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

Reuse

Borrowing it

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

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 Conduit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nickna/conduit/claude-md.svg)](https://agentmods.dev/instructions/nickna/conduit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nickna/conduit/claude-md"><img src="https://agentmods.dev/badge/instructions/nickna/conduit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,838 This file is loaded in full into every session.
When invoked 4,838 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 $0.04838 $0.04838
Opus 5 $0.02419 $0.02419
Sonnet 5 $0.00968 $0.00968
Haiku 4.5 $0.00484 $0.00484

Measured 2d ago against content hash cfbc5138403f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Conduit 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 2d 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.

Makes network callslowCapability

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

- API changes: Test with Swagger UI or curl
CLAUDE.md · 525 lines

How it starts

The opening of the file, as written. The whole thing — 525 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.


⚠️ CRITICAL: Safety First

Commands That WILL Break Development

❌ FORBIDDEN WEBADMIN COMMANDS

These commands break the development container and force a 5+ minute restart:

  • npm run build (anywhere in WebAdmin directory)
  • cd WebAdmin && npm run build
  • ./scripts/dev/dev-workflow.ps1 build-webadmin (production testing only)

Why? The development container uses an isolated .next directory. Running npm build on the host corrupts the container's build state.

✅ SAFE WEBADMIN VERIFICATION

Use these instead:

  • npm run lint - Check ESLint errors
  • npm run type-check - Verify TypeScript types
  • Hot reloading automatically validates code changes

❌ FORBIDDEN DEVELOPMENT COMMANDS

  • docker compose up for development (always use ./scripts/dev.ps1)

If you run forbidden commands, you will:

  1. Break the development environment
  2. Force a restart with --clean (5+ minutes)
  3. Waste time and ignore explicit instructions

Quick Start Guide

Starting Development Services

⚠️ CANONICAL DEVELOPMENT STARTUP:

./scripts/dev.ps1

Available Flags

./scripts/dev.ps1              # Standard startup
./scripts/dev.ps1 -WebAdmin    # Rebuild WebAdmin container
./scripts/dev.ps1 -Clean       # Complete reset (removes all volumes)
./scripts/dev.ps1 -Build       # Force rebuild (uses cache where possible)
./scripts/dev.ps1 -Rebuild     # Full rebuild with --no-cache (nuclear option)
./scripts/dev.ps1 -Logs -LogService webadmin  # Show container logs

Flag Details:

  • -WebAdmin: Restarts WebAdmin container (fixes Next.js issues)
  • -Clean: Removes containers, volumes, node_modules, build artifacts
  • -Build: Rebuilds containers (uses cache where possible)
  • -Rebuild: Full rebuild with --no-cache flag (nuclear option)
  • -Logs [-LogService <name>]: Show container logs for specific service

Read the full file on GitHub · 525 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. 2d ago First seen · 525 lines · 4,838 tokens per session scan A cfbc5138403f

Subscribe to this mod's changes

Conduit CLAUDE.md is an instructions file published in the GitHub repository nickna/Conduit (10 stars, last pushed 9d ago), licensed MIT. It adds 4,838 tokens to every session, about $0.0242 per session on Opus 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 2026-09-04.

Related

Other instructions, from other repositories

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

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

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

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

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