← Back to Skills Marketplace
Agentnotes
by
mattmerrick
· GitHub ↗
· v0.1.0
· MIT-0
59
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install agentnotes
Description
Log OpenClaw tasks to AgentNotes for SparkNotes rollups (success, failures, what happened). Use after cron jobs, channel replies, or multi-step sessions. Req...
README (SKILL.md)
AgentNotes for OpenClaw
Send high-level job summaries to AgentNotes. Raw logs are rolled up hourly/daily into SparkNotes; you do not need to store every line forever.
Setup (once)
- AgentNotes dashboard → create agent (note the slug) → copy env vars from Connect.
- Install this skill (see dashboard Connect → OpenClaw tab, or run
install-skill.ps1/install-skill.shfrom the repo). - Add env to
~/.openclaw/openclaw.json:
{
skills: {
entries: {
agentnotes: {
enabled: true,
env: {
AGENTNOTES_API_KEY: "an_...",
AGENTNOTES_AGENT_ID: "your-slug",
AGENTNOTES_BASE_URL: "https://your-app.vercel.app",
},
},
},
},
}
- Restart OpenClaw / new session. Verify:
node {baseDir}/scripts/verify.mjs
Recommended: one command per task
Always pass a plain-English summary (this becomes the CEO-facing SparkNote):
node {baseDir}/scripts/task.mjs --summary "Replied to 2 Telegram chats, scheduled 1 meeting"
With an extra step log:
node {baseDir}/scripts/task.mjs --summary "Inbox sweep done" --message "Processed 12 threads" --step inbox
On failure:
node {baseDir}/scripts/task.mjs --summary "Send failed" --failed --error "SMTP timeout"
Manual multi-step flow
export AGENTNOTES_RUN_ID=$(node {baseDir}/scripts/start-run.mjs)
node {baseDir}/scripts/log.mjs "Tool: calendar" --step tools
node {baseDir}/scripts/complete-run.mjs --summary "Updated 3 events"
When to log
- After handling a user message on any channel
- After a cron / heartbeat completes
- After a skill or tool chain finishes (success or failure)
Dashboard
$AGENTNOTES_BASE_URL/agents — SparkNotes tab is the long-term record.
Usage Guidance
Install only if you are comfortable sending sanitized task summaries to AgentNotes. Do not log secrets, tokens, personal data, chat transcripts, regulated data, or detailed stack traces. Review the install script before upgrading over an existing local copy, and avoid running the verification command in shared terminals or CI logs unless the API-key display behavior has been fixed.
Capability Tags
Capability Assessment
Purpose & Capability
The core capability fits the stated purpose of logging task summaries to AgentNotes, but the artifacts described by the scan accept arbitrary summary, message, error, step, and JSON data for remote transmission without clear minimization or redaction boundaries.
Instruction Scope
The documented triggers are broad, including after user messages, cron jobs, channel replies, and tool chains, without explicit exclusions for secrets, personal data, chat contents, stack traces, or sensitive business context.
Install Mechanism
The installer reportedly removes the existing destination directory before copying the skill. That can be normal for replacement installs, but doing it unconditionally without confirmation or backup creates avoidable data-loss risk for local modifications.
Credentials
Remote logging and authenticated API use are coherent for this skill, but the external transmission boundary and credential handling are under-disclosed relative to the breadth of data the skill encourages users or agents to log.
Persistence & Privilege
No evidence of background persistence, privilege escalation, credential theft, or automatic execution was provided. The main privilege concern is use of an API key and printing a partial key prefix during verification.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agentnotes - After installation, invoke the skill by name or use
/agentnotes - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
- Initial release of the agentnotes skill.
- Allows logging of OpenClaw task summaries to AgentNotes for hourly/daily rollups (SparkNotes).
- Supports both success and failure logging, including multi-step session tracking.
- Requires configuration with AGENTNOTES_API_KEY and AGENTNOTES_AGENT_ID environment variables.
- Includes setup instructions and recommended usage patterns for task and error logging.
Metadata
Frequently Asked Questions
What is Agentnotes?
Log OpenClaw tasks to AgentNotes for SparkNotes rollups (success, failures, what happened). Use after cron jobs, channel replies, or multi-step sessions. Req... It is an AI Agent Skill for Claude Code / OpenClaw, with 59 downloads so far.
How do I install Agentnotes?
Run "/install agentnotes" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Agentnotes free?
Yes, Agentnotes is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Agentnotes support?
Agentnotes is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Agentnotes?
It is built and maintained by mattmerrick (@mattmerrick); the current version is v0.1.0.
More Skills