agents-error

A reference for diagnosing common failures in AI-agent frameworks, including missing dependencies, incorrect asynchronous calls, and unavailable tools.

In plain words
What is it for?
Use it when agents fail to run, return no agent, ignore tools, or raise errors related to async methods, framework support, factories, or tool setup.
Why use it?
It links visible errors to likely causes and gives an order for checking problems before changing code.

Agent

Install

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.

agentmods
npx agentmods add agents/smart-ai-memory/attune-ai/error
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/attune-ai
Per session 2 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 532 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00002 $0.00532
Opus 5 $0.00001 $0.00266
Sonnet 5 $0.00000 $0.00106
Haiku 4.5 $0.00000 $0.00053

Measured 2d ago against content hash 1c67e5d3b14a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents-error 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.help/templates/agents/error.md · 42 lines

What it actually says

Universal Agent Factory — create, run, and orchestrate AI agents across frameworks

Failure modes

Symptom Cause Fix Severity
RuntimeWarning: coroutine 'BaseAgent.invoke' was never awaited invoke / run called without await They are coroutines — await them or use asyncio.run high
Constructing a non-native factory raises / is_available() is False The framework's optional dependency isn't installed Install the framework extra, or use native; check list_frameworks(installed_only=True) high
recommend_framework / list_frameworks "needs an instance" error Called as if instance-only They are callable on the class; call AgentFactory.list_frameworks() low
get_agent(name) returns None No agent with that name was created on this factory Check list_agents(); names are per-factory low
A tool isn't used by the agent Tool not added / wrong schema Build it with create_tool(...) and pass it via tools= or add_tool(...) medium

Risk areas

  • The run methods are async. invoke, run, and stream are coroutines — forgetting to await is the most common mistake.
  • Non-native frameworks are optional. They load lazily; check is_available() / list_frameworks(installed_only=True) before selecting one.
  • Scope. This feature is the Factory; the release agent team and its state store live under release-prep, not here.

Diagnosis order

  1. Confirm you are awaiting: await agent.invoke(...) / await workflow.run(...).
  2. Confirm the framework is installed: AgentFactory.list_frameworks( installed_only=True).
  3. For a missing agent, check list_agents().
  4. For tool issues, confirm the tool was built with create_tool and attached.
Changes

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.

  1. 2d ago First seen · 42 lines · 2 tokens per session scan A 1c67e5d3b14a

Subscribe to this mod's changes

agents-error 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 532 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.