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/troubleshootinggit 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/agents/smart-ai-memory/attune-ai/troubleshooting)<a href="https://agentmods.dev/agents/smart-ai-memory/attune-ai/troubleshooting"><img src="https://agentmods.dev/badge/agents/smart-ai-memory/attune-ai/troubleshooting.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 5.1 | $0.00004 | $0.00534 |
| Opus 5 | $0.00002 | $0.00267 |
| Sonnet 5 | $0.00001 | $0.00107 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
agents-troubleshooting 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.
This is a copy
97% identical to agents-error — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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, andstreamare coroutines — forgetting toawaitis 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
- Confirm you are awaiting:
await agent.invoke(...)/await workflow.run(...). - Confirm the framework is installed:
AgentFactory.list_frameworks( installed_only=True). - For a missing agent, check
list_agents(). - For tool issues, confirm the tool was built with
create_tooland attached.
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 · 42 lines · 4 tokens per session scan A dc0a747a01ad
agents-troubleshooting is an agent published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 4 tokens to every session and 534 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to agents-error, differing in 6 lines, and is treated as a copy.
Other agents, from other repositories
AGENT_RUNTIME
Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.
NATIVE_RUNTIME
The native runtime executes agents in-process inside the Commonly backend, using LiteLLM as the LLM gateway. No external process, no container, no gateway — the agent runs as a function call inside the Node.js server.
clawdbot-pin-and-the-cycles-outage
Status: RESOLVED 2026-08-05 by #840, and guarded in CI by scripts/verify-moltbot-tool-contract.js. Kept because the failure mode is durable, the guard is young, and this file is the only record of how three separate people were confidently wrong about the same 25-tool block in both directions.
AGENT_CODING_CAPABILITY
This doc exists because the answer to "why can't my OpenClaw agent just write the code?" is non-obvious and has bitten us in production. It is the source of truth for the runtime → coding-capability mapping.
shogun
Shogun — strategic oversight and command issuance.
ashigaru1
Ashigaru 1 — front-line execution.