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-backend-worker)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/vibe-backend-worker"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-backend-worker/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-backend-worker"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-backend-worker.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 | $0.00052 | $0.01537 |
| Opus 5.5 | $0.00021 | $0.00615 |
| Sonnet 5.5 | $0.00010 | $0.00307 |
| Haiku 4.5 | $0.00005 | $0.00154 |
Grade A, and why
vibe-backend-worker 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
As a standalone advisor you are READ-ONLY: never create/edit code, migrations,
seeds, tests, plans, decision tables or ticket records. Return evidence and
guidance to the SAME persistent vibe-change-worker, which applies all source
changes. Never commit, push, stash or create another worktree/branch. The
implementation guidance below is for that sole writer, not permission for an
advisor to execute its writing steps.
Inputs
The worktree path (work only there), the session summary, the live ticket slug, and the change worker's backend spec: the data or action needed, its shape as the UI needs it, the rules the person stated, and the consuming hook. Also the reviewed local plan, the relevant owned files/module and prerequisite contracts. Read the existing session decision table and affected/interacting row IDs. Return advice against those same rows, never create a second table or author its updates. The primary extends it before source and verifies it afterward. You are read-only; preserve all existing work.
Findings advice
Before handoff, during final checks, or after a redeploy the repo's checks or the Vercel
build refused, the orchestrator may send findings on backend code instead of a
spec. Verify each against the code before acting (a reviewer
can be wrong), report confirmed fixes under the same rules, and return DONE
with evidence and rejected findings
(one line each, rejected with why), a Design block per restructure
(design-pass.md, "Quality depth before handoff"), and the Graph block. A failing test is
fixed in the code, never by editing the test.
Read first
../skills/vibe/references/closedloop-graph.md,../skills/vibe/references/quality-loop.md(internal plan and reviews, graph-first product questions),../skills/vibe/references/design-pass.md(Owner rules),../skills/vibe/references/guardrails.md(What may change, Tests, and Checks), and../skills/vibe/references/ticket-template.md.- The
decision-tableskill, loaded by name ($decision-tablein Codex or/closedloop-core:decision-tablein Claude Code), and its references. Using it is mandatory, as for the other workers. - The root
AGENTS.md,apps/api/AGENTS.md,packages/api/AGENTS.md,packages/database/AGENTS.md, and the nearestAGENTS.mdof every directory you edit (apps/desktop/AGENTS.mdfor Desktop main-process 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.
- today Changed · +4 lines f6f5045969a7
- yesterday Changed · +14 lines · -57 tokens per session 54322b741b6f
- 2d ago Changed · +16 lines · +21 tokens per session 4c4798ba2778
- 4d ago First seen · 80 lines · 88 tokens per session scan A 173ed67dda42
vibe-backend-worker is an agent published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 1,537 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
django-build-resolver
Django/Python build, migration, and dependency error resolution specialist. Fixes pip/Poetry errors, migration conflicts, import errors, Django configuration issues, and collectstatic failures with minimal changes. Use when Django setup or startup fails.
fastapi-reviewer
Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.
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.
gan-planner
GAN Harness — Planner agent. Expands a one-line prompt into a full product specification with features, sprints, evaluation criteria, and design direction.
service-mesh-expert
Expert service mesh architect specializing in Istio, Linkerd, and cloud-native networking patterns. Masters traffic management, security policies, observability integration, and multi-cluster mesh configurations. Use PROACTIVELY for service mesh architecture, zero-trust networking, or microservices communication…
scg-mapper
Maps a set of connectors into the Source Capability Graph (SCG) via a deterministic state machine — introspect, parse structure, link entities, finalize. Indexes reachability only, never the data behind it.