What is daimonos AGENTS.md?

Repository instructions for working on Daimonos, a project with tools and conventions for coding agents.

Use them when starting work in the Daimonos repository, especially to check Vikunja project records, repository rules, technical specifications, and architecture decisions.

They tell a new agent where the authoritative project status lives and which project rules, strategies, and design documents to read first.

daimonos AGENTS.md — Instructions file by beardfaceguy

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/beardfaceguy/daimonos/agents-md

Clone the repo

git clone --depth 1 https://github.com/beardfaceguy/daimonos

Made for: Codex, OpenCode.

Per session 7,851 This file is loaded in full into every session.

When invoked 7,851 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.07851	$0.07851
Opus 5	$0.03925	$0.03925
Sonnet 5	$0.01570	$0.01570
Haiku 4.5	$0.00785	$0.00785

Measured yesterday against content hash f4bdf1b2c74e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

daimonos AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

├── shellcheck.rs, curl.rs # shellcheck; structured HTTP

AGENTS.md · 546 lines

How it starts

The opening of the file, as written. The whole thing — 546 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Cross-tool guidance for AI coding agents working in this repository.

Quick start (new agents)

Do these in order. Do NOT skip to reading source code.

Read this file fully — project context, repo layout, conventions.
Go to Vikunja first. Use the Vikunja MCP tools to read the daimonos projects — see Vikunja projects for the id map. This is the authoritative source for what's been done, what's in progress, and what's planned. Most active work lives in project 183 (daimonos-agent). Understand the project state before touching the codebase.
Check .cursor/rules/ — scoped rule files (bounded collections, configurable limits, env inheritance, no thread-spawn in callbacks, resource lifecycle, full-lifecycle tests, repowise).
Check .cursor/strategies/ — Rust collection patterns, memory-safety checklist, testing strategies.
Check docs/ for technical specs, and docs/adr/ for the accepted architecture decision records.
Only then read source code as needed for your specific task.

Daimonos tool usage policy

For repository/workspace operations in this project, use the daimonos MCP server tools by default. This includes file reads/writes, search, exec, git, cargo, docker, snapshots, and workspace introspection.

Prefer execute_script when a task needs 2+ daimonos tool calls.
Use single daimonos tools only for one-off operations.
Use non-daimonos tools only when the target system is external to the workspace (for example Vikunja, GitHub, Atlassian, or web search).

Note: The workspace is the default base for relative paths and the trigram search index. It is not a filesystem boundary — daimonos can read, write, and exec any path on the system. There is no confinement.

What is Daimonos?

Daimonos is a bare-metal operating system purpose-built for AI agents. The kernel, filesystem, process model, and syscall interface are designed from the ground up for agent workloads — no shell, no terminal, no human-facing interfaces.

Read the full file on GitHub · 546 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 · 546 lines · 7,851 tokens per session scan A f4bdf1b2c74e

Subscribe to this mod's changes

daimonos AGENTS.md is an instructions file published in the GitHub repository beardfaceguy/daimonos (2 stars, last pushed yesterday), licensed MIT. It adds 7,851 tokens to every session, about $0.0393 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Planning

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

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).

microsoft/vscode · 6,785 tokens

daimonos AGENTS.md