octomind AGENTS.md

octomind AGENTS.md is an instructions file for Codex, OpenCode from Muvon/octomind. It costs 3,930 tokens per session, scanned A, original, Apache-2.0.

Repository guidance for Octomind, a Rust-based AI development assistant whose model can call tools to read and write files, search, run shell commands, and delegate work. It explains how configuration controls sessions, models, tools, roles, and other behavior.

In plain words
What is it for?
Use it when working on Octomind's command-line interface, sessions, MCP tool routing, configuration, model providers, compression, learning, or background services.
Why use it?
It shows where the main execution flows live and how configuration affects the assistant, reducing the risk of changing one part without updating the connected parts.

Instructions file for CodexOpenCode

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/muvon/octomind/agents-md
Clone the repo
git clone --depth 1 https://github.com/Muvon/octomind

Made for: Codex, OpenCode.

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 octomind AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/muvon/octomind/agents-md.svg)](https://agentmods.dev/instructions/muvon/octomind/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/muvon/octomind/agents-md"><img src="https://agentmods.dev/badge/instructions/muvon/octomind/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,930 This file is loaded in full into every session.
When invoked 3,930 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 5.1 $0.03930 $0.03930
Opus 5 $0.01965 $0.01965
Sonnet 5 $0.00786 $0.00786
Haiku 4.5 $0.00393 $0.00393

Measured 6d ago against content hash a8b451db8c40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

octomind 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 6d 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.

AGENTS.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Octomind — AI Development Assistant (Rust)

Session-based AI assistant where the model calls MCP tools (read/write files, search, shell, delegate) to do real work. Sessions run interactively (CLI), non-interactively (--format), or as daemons (ACP/WebSocket). Config is the single source of truth — all runtime behavior (model, tools, roles, compression, learning) derives from TOML. Multi-provider via octolib. Rust 1.95+, tokio async, clap CLI.

Project Structure

src/
  main.rs              # Entry: CLI parsing → Config::load() → subcommand dispatch
  lib.rs               # Spinner-aware print macros (shadow std::println! etc.)
  config/              # Config types, loading, migrations, log macros
  mcp/                 # Tool routing, server lifecycle, all builtin tools
    core/              # plan, local_tool, functions
    orchestration/     # tap, schedule
    runtime/           # mcp, agent, skill, capability tools
    agent/             # agent_* tool routing → layer/subprocess
  session/
    chat/session/      # ChatSession: init, main loop, command dispatch, API calls
    chat/              # Response processing, tool execution, compression, display
    context.rs         # Session-scoped state (task-local SessionId propagation)
    layers/            # AI sub-agent execution
    guardrails.rs      # Guardrails (pipe) loading and evaluation
    pipe.rs             # Pipe execution logic
    workflows/         # AI-orchestrated multi-step workflows
    learning/          # Cross-session lesson extraction/injection
  acp/                 # ACP stdio server (agent-to-agent protocol)
  websocket/           # WebSocket server for remote sessions
  agent/               # Tap registry, manifest resolution, dependency resolution
  commands/            # CLI subcommand handlers
config-templates/
  default.toml         # ALL config fields with defaults — single source of truth
  agents/              # Agent template files

Where to Look First

Task Start here
Add a new MCP tool src/mcp/core/functions.rs (core) or src/mcp/runtime/mod.rs (runtime) → then route in src/mcp/mod.rs
Add a session command (/foo) src/session/chat/session/commands/mod.rssrc/session/chat/commands.rs
Change a config field/default config-templates/default.toml first, then matching type in src/config/
Trace a config load failure src/config/loading.rsload()
Understand MCP server activation src/config/mod.rsget_merged_config_for_role()
Debug tool not found/routing src/mcp/tool_map.rsget_server_for_tool(), then src/mcp/mod.rstry_execute_tool_call()
Session init / state management src/session/context.rsinit_session_services()
Session main loop src/session/chat/session/main_loop.rs
Response / tool execution flow src/session/chat/response.rssrc/session/chat/response/tool_execution.rs
Skill auto-activation src/mcp/core/skill_auto.rs
Layer / guardrails / workflow src/session/layers/, src/session/guardrails.rs, src/session/pipe.rs, src/session/workflows/
Learning system src/learning/
ACP server src/acp/agent.rs
Sandbox src/sandbox/mod.rs
Directory path constants src/directories.rs

Read the full file on GitHub · 318 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. 6d ago First seen · 318 lines · 3,930 tokens per session scan A a8b451db8c40

Subscribe to this mod's changes

octomind AGENTS.md is an instructions file published in the GitHub repository Muvon/octomind (122 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,930 tokens to every session, about $0.0197 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.