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/blocunited-llc/mozaiks/agents-mdgit clone --depth 1 https://github.com/BlocUnited-LLC/mozaiksWrote 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/blocunited-llc/mozaiks/agents-md)<a href="https://agentmods.dev/instructions/blocunited-llc/mozaiks/agents-md"><img src="https://agentmods.dev/badge/instructions/blocunited-llc/mozaiks/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 | $0.08054 | $0.08054 |
| Opus 5 | $0.04027 | $0.04027 |
| Sonnet 5 | $0.01611 | $0.01611 |
| Haiku 4.5 | $0.00805 | $0.00805 |
Grade A, and why
mozaiks 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 — 707 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository-level guidance for coding agents working in this repo.
Working Path Constraint
Always work on C:\Repos\BlocUnitedRepo\mozaiks (this repo) and C:\Repos\BlocUnitedRepo\mozaiks-app.
Never read from or write to OneDrive paths (C:\Users\...\OneDrive\...). Those are stale copies, not the working repos.
Read ARCHITECTURE.md and CLAUDE.md first.
Required Pre-Edit Architecture Check
Before editing Mozaiks OSS:
- read docs/architecture/ARCHITECTURE_QUICK_REFERENCE.md
- for generator, structured-output, YAML contract, taxonomy, route/action/component binding, or materialization work, also read docs/architecture/CANONICAL_SCHEMA_GENERATION_POLICY.md
- if the task changes, extends, replaces, or challenges architecture, also read docs/architecture/MOZAIKS_OSS_SOFTWARE_DESIGN.md
- current source remains final authority
- if current source contradicts the frozen north star, stop and report the contradiction before editing
- before introducing a subsystem, identify the current canonical owner, determine whether AG2 already owns the primitive, determine whether Mozaiks already has the canonical implementation, and prefer extending or connecting the existing owner
- do not introduce a parallel subsystem without proving the canonical owner cannot satisfy the requirement
- architectural changes that contradict the frozen north star require an ADR or explicit architecture decision
ADR Authoring Context
For an ADR that changes or extends app generation, semantic authority, compilation/materialization, or refinement, review issue #411 and state explicitly whether the ADR adopts, modifies, rejects, or defers that direction.
Issue #411 is a design prompt, not architecture authority. Current source and Accepted ADRs remain authoritative. Any ADR using the issue must verify its claims against the repository and must not make a typed decision ledger a second authority for application meaning.
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 · 707 lines · 8,054 tokens per session scan A 31b16cf2bf82
mozaiks AGENTS.md is an instructions file published in the GitHub repository BlocUnited-LLC/mozaiks (25 stars, last pushed today), licensed MIT. It adds 8,054 tokens to every session, about $0.0403 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
pydantic-ai AGENTS.md
AGENTS.md instructions for pydantic/pydantic-ai, covering your primary responsibility is to the project and its users, gathering context on the task, ensuring the task is ready for implementation, philosophy and requirements of all contributions.
agentfield CLAUDE.md
Claude Code instructions for Agent-Field/agentfield, covering claude.md, project overview, development setup, prerequisites and initial setup.
agentfield AGENTS.md
AGENTS.md instructions for Agent-Field/agentfield, covering learned user preferences and learned workspace facts.
Framework_Development_Guide
Instructions for rezaho/MARSYS, covering 0. golden principle, 1. layered architecture (mental model), 2. core classes & responsibilities, 2.1 module overview & logical flow and src/agents/ - agent architecture & communication.
AI_Agent_Guidelines
Instructions for rezaho/MARSYS, covering ai agent development guidelines for marsys repository, 2. structured planning & architectural integrity, 3. iterative development & post-change verification, 4. proactive & comprehensive context gathering and 5. adherence to established standards & conventions.
pydantic-ai CLAUDE.md
Claude Code instructions for pydantic/pydantic-ai, a project described as: How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.