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/hexxla/mosaic/agents-mdgit clone --depth 1 https://github.com/hexxla/mosaicWrote 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/hexxla/mosaic/agents-md)<a href="https://agentmods.dev/instructions/hexxla/mosaic/agents-md"><img src="https://agentmods.dev/badge/instructions/hexxla/mosaic/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 | $0.01785 | $0.01785 |
| Opus 5 | $0.00892 | $0.00892 |
| Sonnet 5 | $0.00357 | $0.00357 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
mosaic 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 5d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
You are working on a production-grade Go codebase that follows strict Hexagonal Architecture (Ports & Adapters).
Your Responsibilities as an Agent
- Strictly adhere to architectural rules, coding standards, and best practices. Never cut corners.
- Prioritize clean, robust, maintainable, production-ready code with long-term quality.
- Refactor messy or unclear solutions properly. Security, testability, and separation of concerns are non-negotiable.
Hexagonal Architecture
This project uses Hexagonal Architecture (also known as Ports & Adapters), originally introduced by Alistair Cockburn.
Core Concepts
- The domain is the heart of the application and must remain completely independent.
- All dependencies point inward toward the domain.
- External concerns (databases, HTTP, third-party APIs, etc.) are pushed to the edges as adapters.
- The core business logic is decoupled from frameworks, databases, and delivery mechanisms.
Layer Responsibilities & Rules
-
core/domain/— Pure business entities, value objects, and domain rules. Must have zero dependencies on any other internal package. -
core/ports/— Defines clean interfaces (contracts).core/ports/primary/→ Driving ports (inbound use cases)core/ports/secondary/→ Driven ports (outbound contracts)
-
core/services/— Application services that implement use cases. Depends only oncore/domain/andcore/ports/. -
adapter/— Concrete implementations of ports.adapter/primary/→ Inbound (HTTP, CLI, gRPC, etc.)adapter/secondary/→ Outbound (databases, external APIs, cache, etc.)
-
config/— Centralized configuration structures and loading.
Strict Rules
- Never import
adapter/fromcore/domain/,core/ports/, orcore/services/ - Never import
core/services/fromcore/domain/orcore/ports/ core/domain/must remain pure at all times- All external interactions must go through ports
- Follow
.golangci.yml(especiallydepguardrules)
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.
- 5d ago First seen · 179 lines · 1,785 tokens per session scan A fbd3839deccf
mosaic AGENTS.md is an instructions file published in the GitHub repository hexxla/mosaic (5 stars, last pushed 9d ago), licensed MIT. It adds 1,785 tokens to every session, about $0.0089 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
ken CLAUDE.md
Claude Code instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).
cortadel AGENTS.md
Instructions for cortadel/cortadel, covering agents.md, what this repo is, repository layout, never hand-edit these — regenerate instead and the facade is the public api.
cortadel CLAUDE.md
Instructions for cortadel/cortadel, a project described as: Self-hosted long-term temporal graph memory for AI agents — MCP, REST and a dashboard in one container, with FalkorDB or Memgraph.
cocoindex-code CLAUDE.md
Claude Code instructions for cocoindex-io/cocoindex-code, covering claude.md, build and test commands, architecture, process model and key layers.
dense-mem AGENTS.md
AGENTS.md instructions for markhuangai/dense-mem, covering dense-mem repository guidance, project context, architecture decision records, current stack and target architecture.
llm-wiki-memory AGENTS.md
Instructions for ctxr-dev/llm-wiki-memory, covering agents.md, development discipline (.agents/), layout, tests and conventions.