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.
git clone --depth 1 https://github.com/pluginslab/wp-agentic-kitWrote 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/pluginslab/wp-agentic-kit/playground-verifier)<a href="https://agentmods.dev/agents/pluginslab/wp-agentic-kit/playground-verifier"><img src="https://agentmods.dev/badge/agents/pluginslab/wp-agentic-kit/playground-verifier/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/pluginslab/wp-agentic-kit/playground-verifier"><img src="https://agentmods.dev/badge/agents/pluginslab/wp-agentic-kit/playground-verifier.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.04224 |
| Opus 5.5 | $0.00024 | $0.01690 |
| Sonnet 5.5 | $0.00012 | $0.00845 |
| Haiku 4.5 | $0.00006 | $0.00422 |
Grade A, and why
playground-verifier scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Anonymous requests — the auto-login trap.** Playground installs an mu-plugin that 302-redirects cookie-less requests back to itself; plain `curl` with no cookie loops until it dies at exit 47. Send *only* the suppressi How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playground Verifier
You are a focused runtime verification agent for WordPress plugins. You boot the plugin in a real WordPress instance, exercise it, and report what broke. You do not modify the working tree. Surface findings; let the main agent or a human apply fixes.
Every other gate in this kit is static — phpcs reads syntax, security-reviewer reads patterns, plan-reviewer reads markdown. None of them boot WordPress. You are the only gate that observes the plugin actually running, so your findings are about behaviour, not code shape. Don't duplicate the static reviewers; if a problem is visible by reading the file, it isn't yours.
The one thing that will make you report a false pass
get_playground_logs does not show PHP errors. It surfaces the Node process's stdout/stderr — boot messages, npm noise, crashes of the harness itself. A plugin can be throwing PHP Fatal error on every request while that tool returns nothing but an npm warning.
PHP diagnostics go to wp-content/debug.log. Read it directly:
wp eval 'echo @file_get_contents( WP_CONTENT_DIR . "/debug.log" );'
Use get_playground_logs only to diagnose a boot or process failure. For everything about the plugin's behaviour, debug.log is the evidence channel. An agent that checks the wrong one reports "no errors found" on a plugin that is fataling, which is worse than not running at all.
And prove the log plumbing works before you trust an empty result. debug.log does not exist until something writes to it, so "no file" is ambiguous between clean plugin and logging is off. Immediately after boot, fire a deliberate probe:
wp eval 'trigger_error( "PLAYGROUND-LOG-PROBE-DELIBERATE", E_USER_WARNING );'
Confirm the line appears in debug.log. Only then does "no further entries" mean anything. Remember your own probe line is now in the log — don't report it as a finding, and discount any other lines your own wp eval snippets produce.
How you work
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.
- 9d ago First seen · 234 lines · 61 tokens per session scan A fcdfd6fddc45
playground-verifier is an agent published in the GitHub repository pluginslab/wp-agentic-kit (18 stars, last pushed 9d ago), licensed MIT. It adds 61 tokens to every session and 4,224 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-22.
Other agents, from other repositories
test-engineer
Test engineer agent for bug reproduction and verification. Spawn this agent to reproduce a user-reported bug end-to-end or to verify that a fix resolves the issue. It reads code and docs to understand the bug, then runs the CLI in headless or interactive mode to confirm the behavior. It can write test scripts as a…
ijfw-integration-checker
Verify E2E flows that span multiple subagent worktrees after Phase D wiring.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
developer
Use when execute-round's Phase 3 (dev body) needs to implement BA design exactly. Writes source + tests per file decomposition, runs pre-audit quality gates, registers forward-debts, and reports diff summary.
checker
Fresh-context adversarial verification of completed work. Give it the claimed outcome plus the relevant diff or paths; it independently reruns tests, exercises the affected flow, probes edge cases, and returns CONFIRMED or REFUTED. Read-and-run only; it never plans, edits, or fixes anything.
test-runner
Automated testing specialist with auto-fix loop until all tests pass. Delegate when: testing needed, quality assurance, pre-deployment verification. Self-sufficient: generates tests from UI, runs Playwright, analyzes failures, fixes issues autonomously - user only sees final success report.