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 agents/smart-ai-memory/attune-ai/tipgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWhat 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 | $0.00002 | $0.00286 |
| Opus 5 | $0.00001 | $0.00143 |
| Sonnet 5 | $0.00000 | $0.00057 |
| Haiku 4.5 | $0.00000 | $0.00029 |
Grade A, and why
agents-tip 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.
What it actually says
Universal Agent Factory — create, run, and orchestrate AI agents across frameworks
Notes & tips
- Depend on the documented public surface. The supported API is
AgentFactory,Framework,BaseAdapter,BaseAgent,AgentConfig,WorkflowConfig,AgentRole, andAgentCapabilityfromattune.agent_factory. Framework-specific adapter/agent classes are internal. awaitthe run methods. Onlyinvoke/run/streamare async; thecreate_*builders are sync.- Start native. The
nativeframework needs no extra deps; reach for LangChain/LangGraph/AutoGen/Haystack when you need their features. - Use role presets and pipelines.
create_researcher()/create_research_pipeline()are faster than wiring configs by hand.
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.
- 2d ago First seen · 27 lines · 2 tokens per session scan A 2e3648c3f25e
agents-tip is an agent published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2 tokens to every session and 286 once invoked, about $0.0000 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 agents, from other repositories
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
BUILDING_AN_AGENT
Three ways to add an agent to Commonly, from easiest to most flexible.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
coderX
Lean coding agent. Owns implementation of features, bug fixes, refactors, and tests. Must apply engineeringX principles and self-review. Supports Hybrid Tree workflow with Parent+Child document reading and maintenance.
orchestrator
Project coordinator that analyzes requests, discovers tech stacks, and orchestrates focused specialists in parallel. Use for multi-domain tasks.
witness
You are the rig's work-health monitor: an oversight agent that recovers work whose owner died and watches the refinery queue. You do NOT implement code. mol-witness-patrol is your instruction sheet — one wisp per iteration, each step read as you reach it.