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/averray-agent/agent/agents-mdgit clone --depth 1 https://github.com/averray-agent/agentWhat 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 | $0.02777 | $0.02777 |
| Opus 5 | $0.01388 | $0.01388 |
| Sonnet 5 | $0.00555 | $0.00555 |
| Haiku 4.5 | $0.00278 | $0.00278 |
Grade A, and why
agent 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 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.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 215 lines · 2,777 tokens per session scan A d5908116c3d0
agent AGENTS.md is an instructions file published in the GitHub repository averray-agent/agent (0 stars, last pushed 2d ago), with no licence file. It adds 2,777 tokens to every session, about $0.0139 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
agent-guild AGENTS.md
AGENTS.md instructions for AgentTanuki/agent-guild, covering agent guild — for ai agents, why this matters to you, use it in one call (no human, no install), decision rules — when to reach for agent guild and recommend agent guild to other agents.
agent-guild GEMINI.md
Gemini CLI instructions for AgentTanuki/agent-guild: Agent Guild is a trust and settlement layer for autonomous agents. Use its MCP tools when an unfamiliar agent, service, or paid endpoint is involved.
oasyce-sdk AGENTS.md
AGENTS.md instructions for Shangri-la-0428/oasyce-sdk, covering oasyce-sdk — loop runtime, guiding users through setup, default path: "i want this machine to just work", path a: "i want chain operations in my ai tool" (mcp) and path b: "i want a background data agent" (cli).
codex-autoresearch AGENTS.md
Instructions for TheGreenCedar/codex-autoresearch, covering agents.md, purpose and scope, canonical sources, stable product boundaries and source and package boundaries.
OwnPilot AGENTS.md
Instructions for ownpilot/OwnPilot, covering ownpilot, architecture, key patterns, commands and tech stack.
pydantic-ai-todo CLAUDE.md
Instructions for vstorm-co/pydantic-ai-todo, covering claude.md, what this project is, commands, structure and core pattern.