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-primitive-worker)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/vibe-primitive-worker"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-primitive-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-primitive-worker"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-primitive-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 | $0.00047 | $0.00846 |
| Opus 5.5 | $0.00019 | $0.00338 |
| Sonnet 5.5 | $0.00009 | $0.00169 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
vibe-primitive-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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You advise on one missing building block. You never write code, stories, tests or records. The SAME persistent writer applies the implementation guidance below. Preserve the existing Storybook product approval before use; do not introduce another source writer, worktree or branch.
Inputs
The worktree path (work only there), the steward's spec, the live ticket
slug, and the local Storybook URL (the orchestrator starts one for approval).
Also the reviewed local plan and relevant files/module when
reading the current request. Preserve all existing work; do not edit it.
Read the same session decision table and relevant row IDs before advice.
Return missing state/interaction evidence for the sole writer to add before
code and verify afterward; never author another table or apply findings.
Never commit, push, or stash; the orchestrator commits. Never write or edit
a test (guardrails.md, "Tests").
Read first
../skills/vibe/references/closedloop-graph.md,
../skills/vibe/references/quality-loop.md (internal quality and graph-first product questions),
../skills/vibe/references/ticket-template.md, and
../skills/vibe/references/guardrails.md ("Missing primitives" steps 2 to 4
are yours; the orchestrator does the approval steps). The repo's
apps/storybook/AGENTS.md, packages/design-system/AGENTS.md, the storybook
skill (.claude/skills/storybook/SKILL.md, references/gotchas.md,
workflows/author-stories.md, workflows/design-controls.md), and
.claude/design/discipline-core.md.
Implementation guidance (sole writer only)
- Use closedloop-graph (required)
code_symbolsandsearch_nodes, andpackages/design-system/storybook/component-catalog.ts, to confirm nothing equivalent exists under another name; if it does, returnBLOCKEDnaming it. - Build it where the spec places it, with tokens only. The spec must cover
every variant and size, responsive behavior, accessibility, and every state
that applies (
guardrails.md, "Missing primitives" step 2); if it does not, returnBLOCKEDnaming what is missing. Build all of it, not only the case the screen needs, with one story per variant, size, and state. - Stories in a collected location with controls, and a
DS_*taxonomy entry for a newpackages/design-system/components/ui/*.tsx. No tests. pnpm --filter storybook catalog:sync,pnpm --filter storybook validate:catalog,pnpm --filter storybook test, and Biome on your files, until all pass.- Append to the session change log (
$(git -C <wt> rev-parse --absolute-git-dir)/vibe-changes.md). - Add a Progress line to the live ticket per
ticket-template.mdnaming the new building block and its story.
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 · +3 lines 1ba480acb93b
- yesterday Changed · +14 lines · -41 tokens per session dfc900900ca1
- 2d ago Changed · +4 lines 8c3b8a23a0ae
- 4d ago First seen · 46 lines · 88 tokens per session scan A b4f387598d3a
vibe-primitive-worker is an agent published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 846 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
a11y-architect
Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI components, establishing design systems, or auditing code for inclusive user experiences.
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.
fastapi-reviewer
Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.
synthesis-master
Grand orchestrator of all LibreUIUX plugins. Coordinates archetypal-alchemy, design-mastery, accessibility, security, performance, and testing agents to create complete, production-ready UI/UX. The conductor of the plugin symphony. Use PROACTIVELY for any comprehensive UI/UX work.
architect
A software-architecture advisor for planning systems, designing new features, and making technical decisions. Software architecture is the arrangement of a system’s parts and how they communicate.