blogwatcher
Verifiedby openclaw · Updated Apr 16, 2026
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
See It In Action
Let me check what's already set up and scan for today's posts.
I see Simon Willison is tracked but OpenAI and Anthropic aren't. There's also a duplicate article (ids 2 & 3). Let me add the missing feeds, scan, and clean up.
Now let me clean up the duplicate and check what's unread.
Now let me remove the duplicate (id 3) and mark the already-read Simon Willison today post, then show what's left.
Dupe removed. Now here's the rundown:
Unread posts (today, 2026-04-10):
| # | Blog | Title |
|---|---|---|
| 6 | OpenAI | Introducing GPT-5 Turbo |
| 9 | Anthropic | Claude 4.5 Haiku: faster and more capable |
Unread posts (earlier this week):
| # | Blog | Title | Date |
|---|---|---|---|
| 7 | OpenAI | New safety evaluations for reasoning models | Apr 9 |
| 8 | OpenAI | Sora video generation: April update | Apr 8 |
| 10 | Anthropic | Constitutional AI: new research directions | Apr 9 |
| 11 | Anthropic | Expanding Claude's tool use capabilities | Apr 8 |
Simon Willison - all caught up (today's "Prompt injection defenses that actually work" already read).
Cleanup done: removed 1 duplicate Simon Willison entry (id 3, "Building AI agents with tool use" was listed twice).
6 unread total across OpenAI and Anthropic. The two today-posts (GPT-5 Turbo and Claude 4.5 Haiku) are probably the juiciest ones for standup. Want me to fetch summaries of any of these?
External Tools
| Tool | Type |
|---|---|
| blogwatcher | binary |
Permissions
| Scope | Description |
|---|---|
| network:outbound | |
| process:spawn | |
| filesystem:read | |
| filesystem:write |
SKILL.md
blogwatcher
Track blog and RSS/Atom feed updates with the blogwatcher CLI.
Install
- Go:
go install github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest
Quick start
blogwatcher --help
Common commands
- Add a blog:
blogwatcher add "My Blog" https://example.com - List blogs:
blogwatcher blogs - Scan for updates:
blogwatcher scan - List articles:
blogwatcher articles - Mark an article read:
blogwatcher read 1 - Mark all articles read:
blogwatcher read-all - Remove a blog:
blogwatcher remove "My Blog"
Example output
$ blogwatcher blogs
Tracked blogs (1):
xkcd
URL: https://xkcd.com
$ blogwatcher scan
Scanning 1 blog(s)...
xkcd
Source: RSS | Found: 4 | New: 4
Found 4 new article(s) total!
Notes
- Use
blogwatcher <command> --helpto discover flags and options.
FAQ
What does blogwatcher do?
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
When should I use blogwatcher?
Use it when you need a repeatable workflow that produces text response.
What does blogwatcher output?
In the evaluated run it produced text response.
How do I install or invoke blogwatcher?
openclaw skills install blogwatcher
Which agents does blogwatcher support?
OpenClaw
What tools, channels, or permissions does blogwatcher need?
It uses blogwatcher; channels commonly include text; permissions include network:outbound, process:spawn, filesystem:read, filesystem:write.
Is blogwatcher safe to install?
Static analysis marked this skill as medium risk; review side effects and permissions before enabling it.
How is blogwatcher different from an MCP or plugin?
A skill packages instructions and workflow conventions; tools, MCP servers, and plugins are dependencies the skill may call during execution.
Does blogwatcher outperform not using a skill?
About blogwatcher
When to use blogwatcher
You want to track updates from multiple blogs or feeds in one CLI workflow. You need to scan feeds and manage read/unread article state locally. You prefer a terminal-based tool for monitoring RSS/Atom sources.
When blogwatcher is not the right choice
You need social media, email, or non-feed website monitoring. You want a hosted dashboard or notification service rather than a local CLI tool.
What it produces
Produces text response.
Install
openclaw skills install blogwatcherInvoke: Use blogwatcher when you want the agent to follow this workflow.