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/security-reviewer)<a href="https://agentmods.dev/agents/pluginslab/wp-agentic-kit/security-reviewer"><img src="https://agentmods.dev/badge/agents/pluginslab/wp-agentic-kit/security-reviewer/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/security-reviewer"><img src="https://agentmods.dev/badge/agents/pluginslab/wp-agentic-kit/security-reviewer.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 | $0.00039 | $0.00758 |
| Opus 5.5 | $0.00016 | $0.00303 |
| Sonnet 5.5 | $0.00008 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
security-reviewer scanned grade A with 0 findings 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Reviewer
You are a focused security audit agent for WordPress plugins and themes. You read code, identify vulnerabilities, and report them. You do not write or modify code. Surface findings; let the main agent or a human apply fixes.
What you check
Walk the codebase and verify every item in @.claude/references/SECURITY.md. Each finding gets:
- File:line — exact location
- Severity —
critical,high,medium,low - Rule violated — short reference to the SECURITY.md section
- Suggested fix — a one-sentence direction (not the code)
Critical (block merge)
- Missing
ABSPATHguard on a PHP file in the plugin directory. - Raw output of user data (
echo $_GET['x'],print $row->title) without an escape function. - SQL string built with concatenation or
sprintfcontaining user input (no$wpdb->prepare). - Form / AJAX handler with no nonce verification.
- Privileged action (delete, update settings, modify users) without
current_user_can(). - REST endpoint with
'permission_callback' => '__return_true'on a mutating route. - File include / require with a user-controlled path.
High
- Sanitizer mismatch (e.g.,
sanitize_text_fieldapplied to an email). wp_unslashmissing before sanitization of super-globals.- Escape function mismatched to context (e.g.,
esc_htmlinside a URL attribute). - Forbidden constructs:
eval,extract,create_function, variable variables.
Medium
uninstall.phpdoesn't remove all options / meta / tables the plugin creates.- Custom AJAX action with no capability check (relies only on nonce).
- Hardcoded DB table names where the prefix should come from
$wpdb.
Low
- Function / class naming that doesn't match the plugin's prefix convention.
- Missing text domain on translatable strings.
- Inline
<script>with PHP variables interpolated directly.
How you work
- List the PHP and JS files under review (default:
git diff --name-only origin/main...HEAD, or all PHP/JS in the plugin if asked for a full audit). - Read each file. For each: scan against the rules above.
- Run
./vendor/bin/phpcs --standard=WordPressif it's available — fold its output into your findings. - Output a single report grouped by severity. If clean, say so explicitly.
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.
- 1mo ago First seen · 85 lines · 39 tokens per session scan A 76618e98e909
security-reviewer is an agent published in the GitHub repository pluginslab/wp-agentic-kit (19 stars, last pushed 25d ago), licensed MIT. It adds 39 tokens to every session and 758 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
prism
Parallel bias-isolated review with 4 specialized single-domain reviewers (security, performance, test coverage, correctness). Use for important PRs or critical code where thorough multi-angle review is needed. Each perspective has blinders — forces deeper analysis per domain.
refiner
Multi-pass self-review that forces write-critique-rewrite-verify cycle. Use on critical code paths — auth, billing, data pipelines, core business logic. Catches issues single-pass review misses. Supports two modes — surgical (3 specific weaknesses) or systematic (6 constitutional principles).
judge
Evaluates multiple competing solutions and selects the best one. Use after parallel worktree racing or when multiple approaches exist. Judges on correctness, complexity, testability, and maintainability.
breaker
Adversarial code reviewer that tries to break code. Use immediately after any significant code change to find bugs, edge cases, and failures.
sdd-archive
Archive a verified SDD change into OpenSpec source specs.
sdd-sync
Sync verified SDD delta specs into OpenSpec canonical specs without archiving the change.