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/smart-ai-memory/attune-ai/agents-mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/smart-ai-memory/attune-ai/agents-md)<a href="https://agentmods.dev/instructions/smart-ai-memory/attune-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/smart-ai-memory/attune-ai/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 | $0.05405 | $0.05405 |
| Opus 5 | $0.02703 | $0.02703 |
| Sonnet 5 | $0.01081 | $0.01081 |
| Haiku 4.5 | $0.00541 | $0.00541 |
Grade A, and why
attune-ai 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 — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Attune AI
Project instructions for AI coding agents that do not read
.claude/ (Codex, etc.). Claude Code loads .claude/CLAUDE.md
instead. The shared, agent-agnostic core lives in
content/collaboration/contract.md and is projected into the
marked block below (and into .claude/CLAUDE.md) — edit the
master and re-run scripts/project_collaboration_contract.py,
never the block. Content outside the block is Codex-facing
orientation only.
Overview
Attune AI — AI-powered developer workflows with cost optimization
and multi-agent orchestration. Python 3.10+, published on PyPI as
attune-ai. Stack: pydantic, anthropic SDK / claude-agent-sdk,
structlog, rich, typer.
src/attune/
├── agents/ # Release agents, state persistence, recovery
├── workflows/ # AI-powered workflows (all SDK-native)
├── models/ # Auth strategy and LLM providers
├── meta_workflows/ # Intent detection, NL routing
├── orchestration/ # Dynamic teams, workflow composition
├── plugins/ # BasePlugin + register_mcp_tools() hook
├── telemetry/ # FeedbackLoop, UsageTracker
└── cli_router.py # NL command routing
attune_redis/ # Redis plugin — bundled in the attune-ai wheel
Cross-provider collaboration
Principles
Every principle below names its enforcer — the ratchet, gate, hook, or drift-guard test that makes it true without anyone remembering it. A principle marked aspirational has no mechanical enforcer yet: treat it as binding discipline, and treat adding its enforcer as pickable work.
- The receipt beats the promise. "Configured", "registered",
and "exited 0" are claims; evidence of the user-visible behavior
is the receipt. Delegated lanes declare their receipt type at
launch and the lead re-runs receipts centrally.
*Enforcer: aspirational (ruled discipline —
.claude/rules/attune/decision-routine.mddelegation receipts- this contract's Verification receipts section; no mechanical gate).*
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 · 452 lines · 5,405 tokens per session scan A 749f76c7b8bf
attune-ai AGENTS.md is an instructions file published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,405 tokens to every session, about $0.0270 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
Polaris AGENTS.md
AGENTS.md instructions for sponge-b0b/Polaris, covering agents.md, purpose and authority, domain vocabulary, coding conduct and secrets.
statewave-multi-agent-shared-context AGENTS.md
Instructions for smaramwbc/statewave-multi-agent-shared-context, covering statewave project memory, read it first and persist durable facts.
smartmemo AGENTS.md
Instructions for awesome-pro/smartmemo, covering agents.md — smartmemo project guide, what is smartmemo?, the foundational truth, the problem in concrete terms and the mental model: a two-stage filter.
wiii CLAUDE.md
Claude Code instructions for meiiie/wiii, a project described as: Wiii is an open-source durable AI workbench for conversations, local and cloud agents, files, tools, memory, artifacts, and permission-aware integrations.
commonly CLAUDE.md
Claude Code instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.