What is devir CLAUDE.md?

Repository-specific instructions for Claude Code, describing how the devir Go project is built, tested, organised, and operated.

Building devir, running tests and lint checks, understanding its terminal interface and service runner, and working with its Claude Code integration.

They give the coding agent the project’s expected commands, structure, and design patterns so its changes fit the existing codebase.

devir CLAUDE.md — Instructions file by productdevbook

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/productdevbook/devir/claude-md

Clone the repo

git clone --depth 1 https://github.com/productdevbook/devir

Per session 625 This file is loaded in full into every session.

When invoked 625 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.

Model	Per session	Once invoked
Fable 5	$0.00625	$0.00625
Opus 5	$0.00313	$0.00313
Sonnet 5	$0.00125	$0.00125
Haiku 4.5	$0.00063	$0.00063

Measured yesterday against content hash ded3abfcf75a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devir 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 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.

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 · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 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.

Commands

make build        # Build binary to ./devir
make build-all    # Build for all platforms (dist/)
make test         # Run tests
make lint         # Run golangci-lint
make install      # Build and copy to /usr/local/bin
make clean        # Remove build artifacts

Architecture

Devir is a terminal UI for managing multiple dev services. Written in Go using Bubble Tea TUI framework.

Core Components

cmd/devir/main.go     # Entry point, CLI flags, mode selection (TUI vs MCP)
internal/
  config/             # YAML config loading, service validation
  types/              # Shared types (LogLine, LogEntry, ServiceInfo)
  runner/             # Service lifecycle management, log processing
  tui/                # Bubble Tea model, view rendering, keyboard handling
  mcp/                # MCP server for Claude Code integration

Key Patterns

Runner (internal/runner/runner.go):

Manages service processes with platform-specific handling (Unix/Windows)
Channels for log streaming: LogChan (simple mode), LogEntryChan (TUI mode)
Log filtering via compiled regex (filter, exclude patterns)
Port detection and process killing via process_unix.go/process_windows.go

TUI Model (internal/tui/):

Bubble Tea architecture: Model → Update → View cycle
Tab-based service filtering (activeTab: -1=all, 0+=specific)
Auto-scroll with manual override on user scroll
50ms tick for log collection

MCP Server (internal/mcp/mcp.go):

Exposes 7 tools: devir_start, devir_stop, devir_status, devir_logs, devir_restart, devir_check_ports, devir_kill_ports
Uses go-sdk/mcp with stdio transport
Same runner infrastructure as TUI mode

Configuration

Config file: devir.yaml (searched in current dir and parents)

services:
  name:
    dir: relative/path    # Working directory
    cmd: command to run   # Command to execute
    port: 3000            # Port for status display
    color: blue           # Log prefix color

defaults:
  - name                  # Services to start by default

Read the full file on GitHub · 74 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.

yesterday First seen · 74 lines · 625 tokens per session scan A ded3abfcf75a

Subscribe to this mod's changes

devir CLAUDE.md is an instructions file published in the GitHub repository productdevbook/devir (11 stars, last pushed 7mo ago), licensed MIT. It adds 625 tokens to every session, about $0.0031 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.

Code review Data and AI Testing bubble-tea cli developer-tools go mcp

devir CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Commands

Architecture

Core Components

Key Patterns

Configuration

What this file has done since we first saw it

Other instructions, from other repositories

waveloom AGENTS.md

ollama CLAUDE.md

sq AGENTS.md

azure-sdk-for-go go-examples.instructions.md

azure-sdk-for-go go-code.instructions.md

cli AGENTS.md