agentmods.dev

daedalus AGENTS.md

Project-specific instructions for Daedalus, a TypeScript command-line coding tool that routes work between AI models, coordinates multiple agents, and indexes code.

In plain words
What is it for?
Use them when modifying Daedalus so imports, exports, configuration, error handling, architecture, and tests follow the repository’s rules.
Why use it?
They give an AI coding assistant the project’s conventions, structure, and testing expectations before it changes code.

Instructions file for CodexOpenCode

4 2d ago A scan 797 tokens original MIT
View the source file bgill55/daedalus
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/bgill55/daedalus/agents-md
Clone the repo
git clone --depth 1 https://github.com/bgill55/daedalus

Made for: Codex, OpenCode.

Per session 797 This file is loaded in full into every session.
When invoked 797 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 $0.00797 $0.00797
Opus 5 $0.00398 $0.00398
Sonnet 5 $0.00159 $0.00159
Haiku 4.5 $0.00080 $0.00080

Measured 2d ago against content hash 853ec1b5f162, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

daedalus 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 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.

AGENTS.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Daedalus — Agent Conventions

Project Identity

  • Name: Daedalus (daedalus-cli on npm)
  • Description: Local-first AI coding CLI with embedded model router, multi-agent orchestration, and codebase indexing
  • Language: TypeScript (ESM, "type": "module")
  • Node: >=20

Code Conventions

  • No comments in source files unless absolutely necessary for clarity
  • No emoji in code or docs unless user explicitly requests
  • Exports: named exports only (no default exports)
  • Types: Zod schemas in config files, interfaces in src/types.ts
  • Imports: always include .js extension in ESM imports (e.g., './file.js')
  • Error handling: throw typed errors, prefer result pattern for tool returns

Architecture

  • src/index.ts — CLI entry point, REPL loop, command dispatch
  • src/config/ — Zod-schema validated config at ~/.daedalus/config.json
  • src/router/ — Model routing (priority/round-robin/fastest), health checks, rate limiting (token bucket, no global Map)
  • src/session/ — SQLite-backed session persistence, project memory, JSONL export; DB opened via initIndexDb() factory, not at import time; sigma-mem.ts = Σ-Mem reliable memory engine (dedup via content_hash, tag-ranked retrieval, time decay), used by BOTH orchestration and single-agent paths
  • src/agents/ — Multi-agent orchestration (Daedalus/orchestrator, Themis/spec, Metis/planner, Hephaestus/coder, Apollo/reviewer, Asclepius/debugger, Mnemosyne/researcher — each role carries a divine callsign, machine key in parentheses); /autopilot command orchestrates end-to-end feature branches; loop.ts uses dynamic import() for Orchestrator, no circular dependency
  • src/tools/ — 16 built-in tools + MCP transport (stdio + HTTP/SSE)
  • src/indexing/ — FTS5 codebase indexing (TS/JS, Python, Go, Rust, Java, C/C++, C#, PHP, Ruby, Elixir)

Testing

  • Framework: vitest
  • Run: npm test (vitest run, 1326+ tests across 106 files)
  • Tests co-located as *.test.ts under src/

Lint

  • Framework: eslint v10 (flat config)
  • Run: npm run lint (eslint src --ext .ts)

Read the full file on GitHub · 49 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 · 49 lines · 797 tokens per session scan A 853ec1b5f162

Subscribe to this mod's changes

daedalus AGENTS.md is an instructions file published in the GitHub repository bgill55/daedalus (4 stars, last pushed 2d ago), licensed MIT. It adds 797 tokens to every session, about $0.0040 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.

Data and AIPlanningTestingagentic-aiaiclicoding-assistantdeveloper-toolslmstudio
Related

Other instructions, from other repositories

keen-code AGENTS.md

Instructions for mochow13/keen-code, covering keen code, important guidelines, architecture and permission system.

mochow13/keen-code · 273 tokens

juggler AGENTS.md

AGENTS.md instructions for juggler-ai/juggler, covering juggler, build / test / lint / dev, linting, tests and git commits.

juggler-ai/juggler · 3,003 tokens

LitosAiCodingAgent CLAUDE.md

Instructions for nitinmms/LitosAiCodingAgent, covering claude.md and avalonia (litos.gui).

nitinmms/LitosAiCodingAgent · 264 tokens

Tlamatini CLAUDE.md

Instructions for XAIHT/Tlamatini, covering tlamatini - claude.md, project identity, ⚠️ use only tlamatini's agents when asked (mandatory), the newest stone — adding-external-mcp (tracked 2026-08-19) and standing rules (do not weaken).

XAIHT/Tlamatini · 24,022 tokens

guardian-agent AGENTS.md

Instructions for Threat-Vector-Security/guardian-agent, covering repository guidelines, branching (critical), project structure & module organization, build, test, and development commands and runtime restart handoff (critical).

Threat-Vector-Security/guardian-agent · 2,934 tokens

keen-code CLAUDE.md

Instructions for mochow13/keen-code, a project described as: A context-aware terminal-based coding agent written in Go. Supports multiple-providers, MCPs, Subagents, Agent Skills, controllable tool output retention, hashline edits, and more.

mochow13/keen-code · 4 tokens