DevMind CLAUDE.md

Project instructions for DevMind, a local coding assistant powered by a language model running on your computer or a compatible local service.

In plain words
What is it for?
They are for building, running, and changing DevMind, including its C# engine, terminal interface, shell runner, patching tools, memory, and model connections.
Why use it?
They give the agent the project’s structure, technology choices, build process, and design boundaries so it can work in the repository with the right context.

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/pkailas/devmind/claude-md
Clone the repo
git clone --depth 1 https://github.com/pkailas/DevMind
Per session 2,081 This file is loaded in full into every session.
When invoked 2,081 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 $0.02081 $0.02081
Opus 5 $0.01040 $0.01040
Sonnet 5 $0.00416 $0.00416
Haiku 4.5 $0.00208 $0.00208

Measured 2d ago against content hash fa8d56a4fade, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

DevMind 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 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.

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 · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — DevMind Developer Reference

Project Overview

DevMind is a local, LLM-powered agentic coding assistant. It runs an agentic loop — read, search, patch, create, run shell/build — against a target codebase, driven by a local model (LM Studio, Ollama, or any OpenAI-compatible endpoint). Code never leaves your machine.

Architecture: decoupled engine + swappable UI skins. The durable engine lives in C# and is UI-agnostic; the user interface is a thin, replaceable skin over it.

  • Product: DevMind
  • Brand: iOnline Consulting LLC
  • Runtime: .NET 10 (net10.0)
  • Language: C#
  • Default branch: master

Repository Layout

Project Purpose
DevMind.Core The engine. UI-agnostic. Contains LlmClient, LoopDriver, AgenticExecutor, ShellRunner, PatchEngine, MemoryManager, IHistoryStore, LanguageServerRouter, TuiConfig. Boundary interfaces: IAgenticHost (side effects) and ILoopCallbacks (UI-state hooks).
DevMind.TUI Terminal.Gui v2 UI skin. Active development target. Uses TuiAgenticHost (implements IAgenticHost), slash commands (/new, /think, /rules, /dir, etc.), global config at %APPDATA%\devmind\devmind.json.
DevMind.Cli Console UI skin. Reference implementation. Read-only devmind.json in working directory.
DevMind.McpServer MCP server exposing the tool set. References DevMind.Core one-way.
_archive/ Retired projects (old VSIX, diagnostic harnesses). Do not modify.

Build & Run

# Build the entire solution
dotnet build

# Run the TUI
dotnet run --project DevMind.TUI -- --dir <repo> --endpoint <llm-endpoint>

# Run the CLI
dotnet run --project DevMind.Cli -- --dir <repo> --endpoint <llm-endpoint>

Environment Variables

Variable Purpose
DEVMIND_ENDPOINT LLM endpoint URL (overrides default)
DEVMIND_API_KEY API key (overrides default)
DEVMIND_SERVER_TYPE Force backend type (vllm/llama/lmstudio/custom); overrides startup auto-detection
DEVMIND_HISTORY_* History store configuration (SqlServer/Sqlite/Null)
DEVMIND_BUILD_COMMAND Explicit build command for run_build (overrides auto-detection)
DEVMIND_CONTEXT_STRATEGY Force context-management policy (transformer/hybrid/auto); auto (default) picks by measured prompt-cache reuse, seeded by a model-name hint (Qwen3.5/3.6, Mamba, etc.)
DEVMIND_TUI_VERBOSE Show the full firehose in the TUI transcript (disables the quiet filter that hides [CONTEXT]/[TOOL_USE]/[LLM]/[AGENTIC] Iteration churn)
DEVMIND_TUI_DIAG Path to a trace file for the TUI color-stamping/append pipeline (inert when unset)

Read the full file on GitHub · 145 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 · 145 lines · 2,081 tokens per session scan A fa8d56a4fade

Subscribe to this mod's changes

DevMind CLAUDE.md is an instructions file published in the GitHub repository pkailas/DevMind (5 stars, last pushed 14d ago), licensed MIT. It adds 2,081 tokens to every session, about $0.0104 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 2026-08-31.

Related

Other instructions, from other repositories

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

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

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

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 · 4,345 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

next.js 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