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/muvon/octomind/agents-mdgit clone --depth 1 https://github.com/Muvon/octomindWrote 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.
[](https://agentmods.dev/instructions/muvon/octomind/agents-md)<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>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 5.1 | $0.03930 | $0.03930 |
| Opus 5 | $0.01965 | $0.01965 |
| Sonnet 5 | $0.00786 | $0.00786 |
| Haiku 4.5 | $0.00393 | $0.00393 |
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.
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.rs → src/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.rs → load() |
| Understand MCP server activation | src/config/mod.rs → get_merged_config_for_role() |
| Debug tool not found/routing | src/mcp/tool_map.rs → get_server_for_tool(), then src/mcp/mod.rs → try_execute_tool_call() |
| Session init / state management | src/session/context.rs → init_session_services() |
| Session main loop | src/session/chat/session/main_loop.rs |
| Response / tool execution flow | src/session/chat/response.rs → src/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 |
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.
- 6d ago First seen · 318 lines · 3,930 tokens per session scan A a8b451db8c40
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.
Other instructions, from other repositories
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
apex-accelerator vendor-prompting.instructions.md
Vendor prompting best-practice rules for Anthropic Claude and OpenAI GPT-5.6-Terra agents and prompts. Each rule cites a rule ID in the vendor-prompting skill rules.json registry. Validator: npm run lint:vendor-prompting.
autopus-adk GEMINI.md
Gemini CLI instructions for Insajin/autopus-adk, covering autopus-adk harness, 스킬 디렉터리, core guidelines, subagent delegation and file size limit.
agent-ship CLAUDE.md
Claude Code instructions for Agent-Ship/agent-ship, covering claude.md, project overview, commands, docker development (recommended) and local development (no docker).
clawock AGENTS.md
AGENTS.md instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.