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.
npx agentmods add instructions/pkailas/devmind/agents-mdgit clone --depth 1 https://github.com/pkailas/DevMindWhat 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 | $0.00692 | $0.00692 |
| Opus 5 | $0.00346 | $0.00346 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
DevMind AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agent context for the DevMind repository. This file explains what the project is, how it is structured, and how to build it. Tool-use rules and the task-completion contract are supplied separately in the system prompt — this file is project context only and should not repeat them.
What DevMind is
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.
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. When a UI framework hits a wall, the skin is swapped — the engine does not move.
DevMind is not a Visual Studio VSIX extension. That was an earlier, retired architecture (now under
_archive/). Disregard any VSIX, WPF, .NET Framework, ormsbuild DevMind.csprojreferences you encounter — they are obsolete.
Stack
- Language / runtime: C# on .NET 10 (
net10.0) - Persistence: SQL Server for conversation history, via
IHistoryStore(SqlServer / Sqlite / Null providers) - Default branch:
master
Repository layout
DevMind.Core— the engine. UI-agnostic. Agentic loop (LoopDriver,AgenticExecutor),LlmClient, context management,PatchEngine, LSP router,ShellRunner,MemoryManager,IHistoryStore. Boundary interfaces:IAgenticHost(side effects) andILoopCallbacks(UI-state hooks).DevMind.McpServer— the MCP server exposing the tool set. ReferencesDevMind.Coreone-way.DevMind.Cli— console UI skin; reference implementation of the host interfaces (ConsoleAgenticHost).DevMind.TUI— Terminal.Gui v2 UI skin. Active development target._archive/— retired projects (old VSIX, diagnostic harnesses). Do not modify and do not treat as current.
Build & run
Build the solution:
dotnet build
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 · 68 lines · 692 tokens per session scan A 1163fed1e2ac
DevMind AGENTS.md is an instructions file published in the GitHub repository pkailas/DevMind (5 stars, last pushed 14d ago), licensed MIT. It adds 692 tokens to every session, about $0.0035 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.
Other instructions, from other repositories
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.