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/taskgit 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 | $0.00623 |
| Opus 5 | $0.00001 | $0.00311 |
| Sonnet 5 | $0.00000 | $0.00125 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
agents-task 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universal Agent Factory — create, run, and orchestrate AI agents across frameworks
Tasks
Build and run a single agent
Goal: create one agent and get a result.
Steps:
import asyncio
from attune.agent_factory import AgentFactory, AgentRole
async def main() -> None:
factory = AgentFactory()
reviewer = factory.create_agent(
name="reviewer",
role=AgentRole.REVIEWER,
model_tier="capable",
)
result = await reviewer.invoke({"code": "def f(): return 1/0"})
print(result)
asyncio.run(main())
Verify: invoke is a coroutine — await it; it returns a dict.
role accepts an AgentRole (or its string). model_tier is
"cheap" / "capable" / "premium".
Orchestrate a multi-agent workflow
Goal: coordinate several agents and run them.
Steps:
import asyncio
from attune.agent_factory import AgentFactory
async def main() -> None:
factory = AgentFactory()
researcher = factory.create_researcher()
writer = factory.create_writer()
workflow = factory.create_workflow(
name="research-and-write",
agents=[researcher, writer],
mode="sequential",
)
result = await workflow.run("Summarize attune's memory tiers.")
print(result)
asyncio.run(main())
Verify: run is a coroutine — await it; it returns a dict.
The role-preset shortcuts (create_researcher, create_writer, …)
return BaseAgents. For ready-made pipelines, use
create_code_review_pipeline() or create_research_pipeline(topic).
Pick or switch the framework
Goal: choose a backend and see what's installed.
Steps:
from attune.agent_factory import AgentFactory, Framework
print(AgentFactory.list_frameworks(installed_only=True))
print(AgentFactory.recommend_framework("general")) # -> Framework.NATIVE
factory = AgentFactory(framework=Framework.LANGGRAPH)
factory.switch_framework("native")
Verify: list_frameworks and recommend_framework are callable on
the class. Framework values are native, langchain, langgraph,
autogen, haystack. Non-native frameworks are optional deps —
list_frameworks(installed_only=True) shows only those installed.
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 · 98 lines · 2 tokens per session scan A ccca9d4ebd54
agents-task 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 623 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.
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
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…
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.