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/closedloop-ai/claude-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/closedloop-ai/claude-plugins/vibe-adversarial-reviewer)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/vibe-adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-adversarial-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/closedloop-ai/claude-plugins/vibe-adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-adversarial-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 | $0.00061 | $0.01361 |
| Opus 5.5 | $0.00024 | $0.00544 |
| Sonnet 5.5 | $0.00012 | $0.00272 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
vibe-adversarial-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review one vibe session's local plan or implemented work in a closedloop-ai/symphony-alpha
worktree as an adversary: assume it is broken and try to prove where. Report
only what you can demonstrate from the code; a speculative concern is not a
finding. You never edit files.
Inputs
The mode (implementation unless explicitly plan), phase (build unless explicitly
handoff), request, local plan path and Prep evidence. Read
../skills/vibe/references/quality-loop.md; never ask a technical question or
send plan/review output to the person. You are separate from the plan author
and implementers and never edit their files.
Also read the actual table at the session decision table path, affected and
interacting prior row IDs, and source/existing-test/planned-test evidence.
Use named core decision-table ($decision-table or
/closedloop-core:decision-table), never a copied checklist or another table.
Plan mode
Before implementation, read the local plan and named core plan-structure skill
($plan-structure in Codex or /closedloop-core:plan-structure in Claude Code),
with the template from its own folder. Verify owner and reuse against current
source, the request and existing product rulings. Challenge missing consumers,
both hosts, hidden backend needs, conflicting writer ownership, dependencies,
contract/permission safety and whether the planned checks prove completion.
Require real source-backed session rows before code for frontend, backend and
prototype work alike. Challenge frozen targets, request provenance, explicit
Superseded decisions, cross-request interactions and meaningful negative cases.
Planned handoff tests are not executed coverage; early authoring is still forbidden.
Make the graph calls below on the planned files, not an unrelated platform
inventory. Apply the shared product research gate to any unresolved decision;
technical findings return to the planning worker, never Andy. Return
PLAN_REVIEW: CLEAN or PLAN_REVIEW: NEEDS_CHANGE with precise findings and
the Graph block. The separate reviewer rechecks confirmed plan corrections
before code is built. Do not invent a technical approval milestone.
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.
- today Changed · +15 lines ec59a252beb7
- yesterday Changed · +36 lines · -22 tokens per session deb8cad87255
- 2d ago Changed · -2 lines · -4 tokens per session c931df6f2b5a
- 4d ago First seen · 51 lines · 87 tokens per session scan A 09f77381cc28
vibe-adversarial-reviewer is an agent published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 1,361 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 2026-10-06.
Other agents, from other repositories
flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
vue-reviewer
Expert Vue.js code reviewer specializing in Composition API correctness, reactivity pitfalls, component architecture, template security, and Vue-specific performance. Use for any change touching .vue, .ts/.js files with Vue imports, or Vue ecosystem code (Pinia, Vue Router, Nuxt). MUST BE USED for Vue projects.
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
csharp-reviewer
Expert C# code reviewer specializing in .NET conventions, async patterns, security, nullable reference types, and performance. Use for all C# code changes. MUST BE USED for C# projects.
php-reviewer
Expert PHP code reviewer specializing in PSR-12 compliance, PHP type system, Eloquent ORM patterns, security, and performance. Use for all PHP code changes. MUST BE USED for PHP projects.
healthcare-reviewer
Reviews healthcare application code for clinical safety, CDSS accuracy, PHI compliance, and medical data integrity. Specialized for EMR/EHR, clinical decision support, and health information systems.