Agent Toolbelt – Safe Site Operations for AI Agents
by Kostya Tereshchuk 1 (0 reviews)

Agent Toolbelt – Safe Site Operations for AI Agents

Safe hands for your site's AI agent: guarded maintenance operations with dry-run, confirm tokens, a full audit log, and automatic rollback.

Agent Toolbelt ranks #25,868 among WordPress.org plugins with 20+ active installations, a 1/5 rating from 0 reviews, and was last updated Sep 6, 2026. Data from WordPress.org, refreshed twice daily — see methodology.

Compatible with WP 7.1
v1.5.1 Current Version v1.5.1
Updated 2 weeks ago Last Update on 06 Sep, 2026
Refreshed 12 hours ago Last Refreshed on
Top 50% by installs Actively maintained
View on WordPress.org
Rank
#25,868
No change
Active Installs
20+
+53.8%
KW Avg Position
149.7
34.7 worse
Downloads
408
+1 today
Support Resolved
0%
No change
Rating
20%
Review 1 out of 5
1 (0 reviews)

Next Milestone 30

Total Progress 40%
20+ 30+
7,605
Ranks to Climb
-
Growth Needed
8,000,000
Active Installs
Pro

Unlock Exact Install Count

See the precise estimated active installs for this plugin, calculated from real-time ranking data.

  • Exact install estimates within tiers
  • Track install growth over time
  • Milestone progress predictions
Upgrade to Pro
Need 6 more installs to reach 30+

Rank Changes

25,123 26,625 28,128 29,630 31,132 16-09-2026 17-09-2026 18-09-2026 19-09-2026 20-09-2026 21-09-2026 22-09-2026 23-09-2026
25,123 26,625 28,128 29,630 31,132 08-09-2026 09-09-2026 10-09-2026 11-09-2026 12-09-2026 13-09-2026 14-09-2026 15-09-2026 16-09-2026 17-09-2026 18-09-2026 19-09-2026 20-09-2026 21-09-2026 22-09-2026 23-09-2026
Current #25,868
Change
Best #

Upgrade to Pro

Unlock 30-day and 90-day rank history charts with a Pro subscription.

Upgrade Now

Active Installs Growth

Active Installs 0,000,000+
Growth +0.0%
Peak 0,000,000

Downloads Growth

0 10 16-09-2026 17-09-2026 18-09-2026 19-09-2026 20-09-2026 21-09-2026 22-09-2026 23-09-2026
0 10 20 08-09-2026 09-09-2026 10-09-2026 11-09-2026 12-09-2026 13-09-2026 14-09-2026 15-09-2026 16-09-2026 17-09-2026 18-09-2026 19-09-2026 20-09-2026 21-09-2026 22-09-2026 23-09-2026
Downloads
Growth
Peak

Upgrade to Pro

Unlock 30-day, 90-day, and yearly download history charts with a Pro subscription.

Upgrade Now

Reviews & Ratings

1.0
0 reviews
Overall 20%
5
0 (0%)
4
0 (0%)
3
0 (0%)
2
0 (0%)
1
0 (0%)

Track This Plugin

Get detailed analytics, keyword tracking, and position alerts delivered to your inbox.

Start Tracking Free

Plugin Details

Version
1.5.1
Last Updated
Sep 06, 2026
Requires WP
6.9+
Tested Up To
7.1
PHP Version
8.0 or higher
Author
Kostya Tereshchuk

Support & Rating

Rating
★ ☆ ☆ ☆ ☆ 1
Reviews
0
Support Threads
0
Resolved
0%

Keywords

Upgrade to Pro

Unlock keyword rankings, search positions, and detailed analytics with a Pro subscription.

Upgrade Now

Frequently Asked Questions

Common questions about Agent Toolbelt – Safe Site Operations for AI Agents

No. The defaults are the product: read-only and low-risk maintenance abilities are on, the destructive ones (update, rollback, toggle, database cleanup) are off, every call is audited, and the status strip at the top of the settings page confirms it at a glance. You only open the settings when you want to grant more (enable a high-risk ability), grant less (observe mode), or try an ability yourself on the Run tab.
No — the application password is only for agents that talk to the site over the network. An agent with shell access uses the built-in WP-CLI commands (wp agent-toolbelt list, wp agent-toolbelt run <ability>, wp agent-toolbelt log) with the same guardrails, dry-run/confirm flow, and audit logging. What the plugin adds for such an agent is exactly the point: guarded, previewable, logged operations instead of raw destructive shell commands.
"Safe" here means: previewed, confirmed, backed up, health-checked, and rolled back automatically if the site breaks — with an audit trail. That's more protection than a human clicking "Update now" gets. It's still a change to your site, which is why the ability ships disabled and you must enable it deliberately.
Several layers: the destructive abilities are off by default; if you enabled them, execution needs a fresh one-time confirm token from a prior dry-run of the same request (a single malicious instruction can't do both steps blindly); every call needs an authenticated administrator — content on your pages can't call anything by itself; the hourly rate budget stalls a stampede; and observe mode lets you cut all write access with one checkbox while you investigate. The honest part: if your agent has admin credentials and is fully compromised, no plugin can save you — the toolbelt's job is to make the destructive path narrow, slow, and visible.
WordPress core's temporary-backup mechanism skips plugins that live in a single file, so there would be no backup to roll back to. Rather than update without a safety net, the ability refuses and tells the agent to use wp-admin or WP-CLI instead.
Everything except the abilities that change plugin files or state: update-plugin, rollback-plugin, and toggle-plugin refuse on multisite with a clear reason instead of guessing at network-wide semantics. Since 1.4 the audit log also heals itself on multisite: if a subsite is missing its log table (network activation only creates it on the main site), the first write creates it.
No. Every ability requires a logged-in user with manage_options (updates also need update_plugins). Anonymous REST calls get a 401, and the abilities don't even appear in the listing for unauthorized users.
Two ways: untick abilities on the Settings → Agent Toolbelt page (they unregister instantly), or add define( 'AGENT_TOOLBELT_DISABLED', true ); to wp-config.php — the kill switch unregisters everything: abilities, REST exposure, and the WP-CLI command. There is also a softer option: observe mode (see below) keeps the abilities visible but read-only.
A read-only switch for the whole toolbelt. While it is on (checkbox on the settings page, or force it with define( 'AGENT_TOOLBELT_OBSERVE', true ); in wp-config.php), agents can still call read-only abilities and preview any operation with dry-run, but every real change is refused with the machine-readable reason observe_mode and a message telling the agent to ask you. Useful while you are getting to know a new agent, or any time you want eyes-only access without hiding the tools.
Not for long. Real executions are rate-limited per user with a fixed hourly budget: 5 high-risk and 30 total mutating executions per hour by default (the agent_toolbelt_rate_budgets filter changes the numbers; define( 'AGENT_TOOLBELT_NO_RATE_LIMIT', true ); disables the limit for supervised bulk-maintenance sessions). Over-budget calls are refused with the reason rate_budget and a retry_after_s hint, and land in the audit log as denied — so a stampeding agent both stalls and leaves a visible trail. Dry-runs and read-only abilities are never counted: diagnosis stays free.

Sign In / Register

You need to sign in or register to use this feature.