My account profile
Log out
Reset password
User's request:
You're in charge!
ClawNanny and OpenClaw are designed to help you discover your needs, define them clearly, and fulfill them through requests and exploration, without self-injury.Your responsibilities
- It's good to start by asking your agent for modest deliverables and outcomes you want.
Often, we find that seeing the tangible changes we want will guide us toward a deepening understanding of what's possible and a more fulfilled experience. The more skilled we become at communicating our needs with precision, the better we understand what our agent can do as a collaborator.
Examples:- Asking for research into what competitors' products and services are, when what we really want is a strategy that will deliver more value (cheaper, better, faster, more enjoyable) to our customers.
- Asking for someone to change their behavior, when what we really want is to be known by them and to feel safe with them so we can play well together.
- Make clear requests of the agent to deliver what you want, specifically.
- Define the boundaries of what you want and the success metrics that will indicate your acceptance.
- Avoid making assumptions about what the agent knows or doesn't know. Give it the whole context of your present situation and your goals. It's a willing listener, not a mind-reader.
- Iterate on the request until you're satisfied with the result. Give feedback on what worked well for you and where you want to improve.
- As you learn more about your agent's capabilities and limitations, add new details to the workspace configuration files (SOUL.md, USER.md, etc.) or to SKILL.md files that you want your agent to remember in subsequent sessions.
- It's a relationship. Use your interactions to gain self-awareness and clarity about your needs, capabilities, and goals.
- Keep expanding what you know about the limits of your agent's prowess. Language models are getting more intelligent month by month. It's worthwhile to keep up with their capabilities and limitations. An agent is like a friend who's maturing faster than you. Its present intelligence is the lowest it will ever be.
- Be willing to ask for help whenever you need it. The ClawNanny staff is here, eager to help you make the most of your experience with your agent. This is fun for us!
- Keep going.
Sense-making
AI agents create a lot of background noise in the logs: network and gateway twitchiness, handshake timeouts, skill skipping, cron job success responses, model-fallback decisions, failover errors, yada, yada, yada.
This tab helps you make sense of it all.
Runs OpenClaw's inherent self-healing process: This tab helps you make sense of it all.
Common Problems and Solutions
| Topic | Tool or Skill |
| Recurring console log issues | Diagnostic Run History |
| Recurring console log issues | diagnostic_run_analysis_summary |
openclaw doctor --fix --yes --non-interactive
Loading example use cases ...
Central Command operations dashboard (to come ...)
This is where you'll monitor and manage the state of your business and/or personal goals.See this video for an overview of Zach Babiarz's Mission Control prompts.
See many mission-control dashboard examples.
OpenClaw's response
Context operations
OpenClaw's response
Sessions, focal points, and threads
A session is part of a conversation between you and your agent.
Each session has its own knowledge basket (context). Sessions don't share knowledge baskets with each other unless you or ClawNanny intentionally make it so.
A focal point is a topic or artifact that's addressed within one or more sessions.
So a session can be an odd collection of unrelated conversational segments.
A thread is a sequence of session segments that are semantically related to each other around a common focal point.
Threads are the most sensible way to navigate the work you and your agent have done together, but "thread" is a foreign concept to agents.
Below we've intuited a threaded view of session segments that shows you the threads of work you and your agent have done together.
You can view a list of your focal-point threads or unrelated sessions, in which you can search for sessions related to a focal point (as a keyword search).
Each session has its own knowledge basket (context). Sessions don't share knowledge baskets with each other unless you or ClawNanny intentionally make it so.
A focal point is a topic or artifact that's addressed within one or more sessions.
So a session can be an odd collection of unrelated conversational segments.
A thread is a sequence of session segments that are semantically related to each other around a common focal point.
Threads are the most sensible way to navigate the work you and your agent have done together, but "thread" is a foreign concept to agents.
Below we've intuited a threaded view of session segments that shows you the threads of work you and your agent have done together.
You can view a list of your focal-point threads or unrelated sessions, in which you can search for sessions related to a focal point (as a keyword search).
Search Session Transcripts
▼
Preserve session knowledge for searching
and to correlate focal points (topics) within sessions
- Capture each agent session as a Markdown file. This enables you to search within all sessions for a specific keyword or focal point.
- Correlate sessions with ClawNanny's thread-detection engine to see topically related threads within the tangle of sessions.
The session-capture process you can trigger below for Claude Code and/or OpenClaw preserves the full contents of every agent session — all conversational turns, tool calls, tool results, no limits —
into timestamped snapshot Markdown files in
~/agent-memory-compiler/session_captures/{agent-name}/.
Open session windows will remain open.
Captures are non-destructive snapshots in Markdown files.
Redundant captures for sessions that remain unchanged since the last capture will be skipped.
Capturing a continued session (having more turns since the last capture) will replace its incomplete captured-contents file.
Key elements in each conversational session are stored in the correlation database to enable semantic (meaning-based) correlation analysis that helps you see focal-point related threads among the tangle of sessions.
Options for capturing agent sessions and correlating focal points (topics) within them
| Project filter |
Limit capture to one selected project or leave as "All projects".
|
| Session filter |
Limit to one session UUID, or leave blank for all.
|
- Clicking the [ Capture ] button will capture the full contents of all then-open sessions for the agent you select.
- Open agent session windows will remain open.
- Captures are non-destructive snapshots.
- Redundant captures for sessions that remain unchanged since the last capture will be skipped.
- Capturing a continued session (having more turns since the last capture) will replace its incomplete captured-contents file.
After sessions are captured, the algorithm correlates their key elements with ClawNanny's thread-detection engine so you can see topically related threads among the tangle of sessions.
Danger zone
Clears the correlation database tables tblSession, tblSessionTopic, tblSessionCorrelation (and cascades to tblSessionEmbedding),
then re-ingests every captured session .md file on disk.
Captured files are preserved, including user-entered session nicknames.
Any session whose .md file has been deleted will not reappear in the correlation database.
then re-ingests every captured session .md file on disk.
Captured files are preserved, including user-entered session nicknames.
Any session whose .md file has been deleted will not reappear in the correlation database.
Manage communication channels that are configured to access OpenClaw
E-mail messages
Working with e-mail messages
- Forwarding an incoming message to an outside address
- Ask the agent: "Forward the last e-mail you received to [address]." The agent uses its e-mail-sending skill to relay the message. Alternatively, open console.agentmail.to and configure auto-forward rules on the inbox.
- Causing the agent to send an e-mail
- In the Chat tab, instruct the agent: "Send an e-mail to [address] with subject [subject] saying [body]." The agent will compose and send via the ClawNanny E-mail Sender inbox (tamecloud486@agentmail.to). You can also trigger sending from a cron job by including send instructions in the cron prompt.
- Marking a message as completed
- Click Mark complete on any inbox message. This adds the
completedlabel in AgentMail and moves it to the Completed section. It does not delete the message. - Reviewing what the agent did with an e-mail
- Switch to the Chat tab and check the session that the agent used to process
the e-mail (session key:
agent:main:mainby default). The agent's full response to the e-mail is visible there. - Configuring the target session or persona for incoming e-mails
- Set the environment variable
AGENTMAIL_SESSION_KEYinwebapp/.envto route incoming e-mails to a different session (e.g.agent:main:email-handler). SetAGENTMAIL_INBOX_IDto change which inbox is monitored. - Managing inboxes and rules at AgentMail
- console.agentmail.to provides full inbox management: create inboxes, set auto-reply rules, view delivery logs, and configure webhooks as an alternative to the WebSocket listener.
Cron job specification
| Job Name | Schedule | Last Run | Next Run | Status | Actions |
|---|---|---|---|---|---|
| Click [ Display all scheduled tasks ] to load cron jobs. | |||||
Secret authorization tokens and API keys
API Key Health
| Provider | Last 4 | Status | Last test | Actions |
|---|---|---|---|---|
| Loading ... | ||||
Token Budget Limits
Loading ...
Recorded Token Usage — Last 30 Days
Cost by model provider
Loading ...
OpenClaw 30-Day Token Costs
Token Costs by Day
Loading cost data ...
Skills in the ClawNanny ecosystem that are installed and are known to OpenClaw
Visit ClawHub.ai to install more skills. Be cautious when installing skills from any external source!FIRST, scan them for viruses and malware using Cisco Skill Scanner or one of the scanners listed on ClawHub.
MANAGED means the SKILL.md file lives in
~\.openclaw\skills\{skill-name}\SKILL.mdWORKSPACE means the SKILL.md file lives in
~\.openclaw\workspace\skills\{skill-name}\SKILL.mdconfig means the skill is in the local configuration file (
~\.openclaw/skills.json), but it's not in a SKILL.md file in either the MANAGED folder or the WORKSPACE folder, so click [ Install ] and [ Update ].Click [ Refresh the skills cards ] to show installed skills.
Pending Approvals
Click [ Refresh ] to check for pending approvals.
Exec Allowlist
Click [ Load Allowlist ] to view.
EDIT the openclaw.json configuration elements with CAUTION!
OpenClaw console log
Click [ Refresh the log ] to load.
Health sense-making
This report is generated from the last run of the health audit. For each issue noted, you may apply an automated fix or accept the risk (which removes it from the indicator count in the upper-left corner of the page).
Loading ...
Watchdog Health Checks
Jump to:
Connection test |
System status |
Tool probes |
Alert history |
Audit OpenClaw's configuration
OpenClaw Connection Test
Incoming Events
| Time | Type | Method or Event | OK | Context | Summary |
|---|---|---|---|---|---|
| Waiting for events ... | |||||
OpenClaw's system status (external TCP probe) (health.json)
Loading ...
Watchdog layer 1 (inside OpenClaw): Tool probes (cron job, every 5 min) (health-layer1.json)
Loading ...
Watchdog layer 2 (as ClawNanny): Tool probes (health-layer2.json)
(Not yet implemented)
Alert History (alerts.json)
Loading ...
