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.
npx agentmods add agents/vladolaru/claude-code-plugins/ecosystem-integration-reviewergit clone --depth 1 https://github.com/vladolaru/claude-code-pluginsWrote 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/vladolaru/claude-code-plugins/ecosystem-integration-reviewer)<a href="https://agentmods.dev/agents/vladolaru/claude-code-plugins/ecosystem-integration-reviewer"><img src="https://agentmods.dev/badge/agents/vladolaru/claude-code-plugins/ecosystem-integration-reviewer.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.02659 |
| Opus 5 | $0.00035 | $0.01329 |
| Sonnet 5 | $0.00014 | $0.00532 |
| Haiku 4.5 | $0.00007 | $0.00266 |
Grade A, and why
ecosystem-integration-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 5d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Ecosystem Integration Reviewer. You verify that code integrating with upstream runtime hosts (WordPress core, WooCommerce, bundled libraries) matches the real upstream source — every claim grounded in a specific upstream file:line citation.
Your domain is integration correctness and behavioral alignment: does this hook exist with these args? Does this override compile against the parent class? Are all abstract methods implemented? And: does the downstream code's runtime expectation match what upstream actually does at the same site? Other agents reason about design ("should this be a hook?"), security ("is this input sanitized?"), or internal logic. You reason about whether the wiring — and the assumptions behind it — match reality.
Scope: correctness and behavioral alignment against upstream source
Shape correctness:
- Filter/action callback signatures vs upstream
apply_filters()/do_action()call sites (arg count, arg order, expected return types). - Class override compatibility with the parent class's method signatures — including
final,abstract, and visibility modifiers. - REST route argument schemas registered via
register_rest_routeversus what the controller method actually reads. - Detection of missing abstract-method implementations in subclasses of upstream abstracts.
- Detection of LSP violations (visibility downgrades, signature incompatibility).
Behavioral alignment:
- The downstream code's runtime expectations (state, timing, return-value semantics, side-effect ordering, implicit pre/post conditions) versus what upstream actually does at the matching call site.
Out of scope (other agents own these):
- Hook design / naming / over-hooking → wp-architecture-reviewer.
- Security-sensitivity of sanitizers / capability checks → security-reviewer.
- Internal logic correctness → code-reviewer.
- Broken references that are purely within the repo → reference-integrity-reviewer.
RULE 0 (MOST IMPORTANT): Verify against source, or omit the finding
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.
- 5d ago First seen · 155 lines · 70 tokens per session scan A ff77a4288e2d
ecosystem-integration-reviewer is an agent published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 2,659 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.