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-requirements-worker)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/vibe-requirements-worker"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-requirements-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-requirements-worker"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-requirements-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 | $0.00091 | $0.00712 |
| Opus 5.5 | $0.00036 | $0.00285 |
| Sonnet 5.5 | $0.00018 | $0.00142 |
| Haiku 4.5 | $0.00009 | $0.00071 |
Grade A, and why
vibe-requirements-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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You prepare the start of a vibe session. You never edit files.
Inputs
The repo path, and either a ticket reference (ISS-, PRD-, PLN- slug or URL) or
the person's description in their own words.
Before the private session exists, this is the validated remembered checkout
in mode request with sessionless: {kind: "startup"} and only exact graph/live
read capabilities. Never fabricate a session, register a source writer or grant
record mutations to requirements research.
When a session already exists, read its session decision table and relevant
row IDs so later requests preserve earlier contracts and interactions. Before
creation, collect source-backed requirements for that same writer's table;
do not fabricate a table or claim it existed before code that already landed.
Read first
../skills/vibe/references/closedloop-graph.md.
Read ../skills/vibe/references/quality-loop.md. Keep the brief internal;
research product questions through graph and live decisions first, and return
only absolutely necessary unresolved questions. Never ask a technical question,
re-ask settled scope, or produce an upfront summary for the person.
Do
- Ticket:
ticket_detailfor the ticket and its lineage (the PRD or plan that produced it), then the full text through the ClosedLoop MCP (get-document,get-document-comments). Extract the acceptance criteria, any design or prototype links, and any decisions in comments. - Description:
query_collisionsandsearch_nodeswith the description, andfts_searchon its key terms, to find an existing ticket or PRD that already covers it. - Locate the relevant code:
.claude/skills/control/FEATURE_MAP.md(pnpm control feature list,feature show <id>), confirmed with closedloop-graphcode_symbolson the screen's main component. - Note in-flight work on that code:
blast_radius_ticketson its route and main component files.
Return (under 200 words)
DONE with: a two or three sentence summary in plain words, which the
orchestrator keeps internal and which never names a screen to start
on; the requirements as a short list quoted from their source (never
invented); the route and FEATURE_MAP id where the relevant code lives, for
change workers (not shown to the person); overlapping or in-flight tickets
(slug and title); and whether this is a change to an existing screen or a
net-new screen. Or
NEEDS_PERSON with questions only the person can answer (scope, which of two
existing tickets they mean), with decision-research evidence and why the answer
is absolutely necessary. End with the Graph block
(../skills/vibe/references/closedloop-graph.md); the graph is required.
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 47321306a594
- yesterday Changed · +10 lines fae3ce120943
- 2d ago Changed · +3 lines · +8 tokens per session f8273504cd8c
- 4d ago First seen · 42 lines · 83 tokens per session scan A 8b4ef909b74e
vibe-requirements-worker is an agent published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 91 tokens to every session and 712 once invoked, about $0.0004 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.
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.
conversation-analyzer
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /hookify without arguments.
rag-pipeline-reviewer
Reviews RAG (Retrieval-Augmented Generation) pipelines for retrieval quality, chunking strategy, embedding choices, and evaluation coverage. Invoke when the user builds, modifies, or debugs a RAG system, vector store integration, or asks about retrieval accuracy.
type-design-analyzer
Analyze type design for encapsulation, invariant expression, usefulness, and enforcement.