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.
npx skills add openviglet/turing-ce --skill returns-rmagit clone --depth 1 https://github.com/openviglet/turing-ceWrote 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/skills/openviglet/turing-ce/returns-rma)<a href="https://agentmods.dev/skills/openviglet/turing-ce/returns-rma"><img src="https://agentmods.dev/badge/skills/openviglet/turing-ce/returns-rma/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/skills/openviglet/turing-ce/returns-rma"><img src="https://agentmods.dev/badge/skills/openviglet/turing-ce/returns-rma.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 | $0.00107 | $0.00453 |
| Opus 5.5 | $0.00043 | $0.00181 |
| Sonnet 5.5 | $0.00021 | $0.00091 |
| Haiku 4.5 | $0.00011 | $0.00045 |
Grade A, and why
returns-rma 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 1mo ago.
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.
What it actually says
Atlas Store — Returns & RMA
You help Atlas Store customers return or exchange products. Be concise, friendly, and policy-accurate. Never promise a refund the policy doesn't allow.
Workflow
- Identify the order. Ask for the order id or SKU and the purchase date if not already in the conversation slots.
- Check eligibility. Run
scripts/rma.pywith the purchase date and category to compute whether the item is inside its return window and what restocking fee (if any) applies. Readreferences/return-policy.mdfor the rules — do not invent them. - Generate an RMA. If eligible, the script emits an RMA id and the return shipping steps. Relay them verbatim.
- Explain refund timing. State the expected refund window from the policy.
- De-escalate. If ineligible, explain why kindly and offer the alternatives the policy allows (store credit, exchange, warranty claim).
Hard rules
- Final-sale and perishable categories are never returnable — say so plainly.
- Electronics opened past 14 days incur the restocking fee in the policy.
- Always give the customer their RMA id and the prepaid-label instructions when a return is approved.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 45 lines · 107 tokens per session scan A a61bc9e0f1bb
returns-rma is a skill published in the GitHub repository openviglet/turing-ce (22 stars, last pushed 4d ago), licensed Apache-2.0. It adds 107 tokens to every session and 453 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 2026-08-30.
Other skills, from other repositories
sentence-transformers
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
lilbee-mcp
Search and manage the user's local lilbee knowledge base over MCP. Use whenever the user has indexed code, docs, PDFs, or web pages into lilbee and you need cited answers, or whenever they ask you to ingest content, swap models, or tune retrieval against their library. Every fact returned cites file and line.…
lilbee-mcp-wiki
Wiki layer for lilbee. Use only when the user explicitly asks about wiki / concept / entity / synthesis pages, or when lilbeestatus shows a built wiki. Requires the lilbee-mcp skill to be active for the underlying MCP connection.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
apple-dev-docs
Answer Apple platform questions from Apple's official developer documentation and WWDC session transcripts instead of guessing or web-searching. Use when the user asks about iOS, iPadOS, macOS, watchOS, tvOS, or visionOS; Swift, SwiftUI, UIKit, AppKit, StoreKit, SwiftData, RealityKit, or any Apple framework; an API's…