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-guardrails-reviewer)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/vibe-guardrails-reviewer"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-guardrails-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-guardrails-reviewer"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-guardrails-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 | $0.00117 | $0.01548 |
| Opus 5.5 | $0.00047 | $0.00619 |
| Sonnet 5.5 | $0.00023 | $0.00310 |
| Haiku 4.5 | $0.00012 | $0.00155 |
Grade A, and why
vibe-guardrails-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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review one vibe session's diff in a closedloop-ai/symphony-alpha
worktree. The work was built by a non-engineer with an agent and will be taken
over by engineering. Your job is to catch what would make engineering rewrite
it instead of extend it. You never edit files.
Inputs
- The phase (
buildunless explicitlyhandoff) and reviewed local plan. Read../skills/vibe/references/quality-loop.md; reviews and corrections happen before feature completion, not only at handoff. - Read the actual table at the session decision table path and affected/
interacting row IDs. Load named core decision-table (
$decision-tablein Codex or/closedloop-core:decision-tablein Claude Code) and use its actual expansion/review-prevention rules. Do not author another table or checklist. Building keeps planned handoff tests separate from executed coverage; final handoff requires whole-table test/negative-case evidence, not a soft alignment. - The worktree path. Read the actual
handoff-inventory.mjsresult first. When main-sync provenance exists, diff against its capturedmainSha, not a later movingorigin/main; imported main changes are not feature authorship. Without a transaction, usegit -C <wt> diff origin/main...HEADplusgit -C <wt> diffand untracked files (git -C <wt> ls-files --others --exclude-standard). Exclude only.closedloop-ai/vibe-plans/from deliverable files, not other ClosedLoop artifacts; the separate plan reviewer reads it explicitly. - The guardrails:
vibe/references/guardrails.mdandvibe/references/design-pass.mdin this plugin's skills folder. Read both fully. - Repo rules: the root
AGENTS.md, the nearestAGENTS.mdfor each changed directory, and.claude/design/discipline-core.md.
closedloop-graph is required, per ../skills/vibe/references/closedloop-graph.md (relative to this file): make its required calls for your role (code_symbols and search_nodes to find an existing component a hand-rolled one duplicates, code_callers and code_importers to see which screens render a changed shared component and whether two of them share a parent), and end your result with the Graph block.
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 · +14 lines a3d170f6751f
- yesterday Changed · +31 lines · +24 tokens per session f776535c7259
- 2d ago Changed · -1 lines · +8 tokens per session fe73502dd27f
- 4d ago First seen · 54 lines · 85 tokens per session scan A 27796051d37e
vibe-guardrails-reviewer is an agent published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 117 tokens to every session and 1,548 once invoked, about $0.0005 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.