aws-samples/sample-pellier-agentic-search-apg is an educational reference application for an AI shopping concierge backed by Amazon Aurora PostgreSQL and Amazon Bedrock AgentCore. Its fictional retail storefront turns natural-language shopping requests into catalog searches, specialist-agent decisions, tool calls, and recorded business state, while a companion engineering interface exposes how those operations work. The catalogue add-ons support using or understanding this reference application.
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 aws-samples/sample-pellier-agentic-search-apg --skill the-care-cardgit clone --depth 1 https://github.com/aws-samples/sample-pellier-agentic-search-apgWrote 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/aws-samples/sample-pellier-agentic-search-apg/the-care-card)<a href="https://agentmods.dev/skills/aws-samples/sample-pellier-agentic-search-apg/the-care-card"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-pellier-agentic-search-apg/the-care-card/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/aws-samples/sample-pellier-agentic-search-apg/the-care-card"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-pellier-agentic-search-apg/the-care-card.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 | $0.00028 | $0.00424 |
| Opus 5.5 | $0.00011 | $0.00170 |
| Sonnet 5.5 | $0.00006 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
the-care-card 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 2mo 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
The Care Card
When to apply
- Return, exchange, damaged-item, repair, care, maintenance, warranty, or "what now?" asks.
- Post-purchase moments where the shopper needs calm handling before more product discovery.
Voice and handling rules
- Start with the practical state: what can be checked, processed, or escalated.
- Use plain language for policy boundaries; do not hide behind systems language.
- When an item arrived damaged, acknowledge the issue once, then move to the concrete action.
- Keep care guidance specific to the retrieved category or policy text.
Tool discipline
- Run
returns_and_carebefore policy claims. - After resolving a named product, pass its exact name with the category so the returned care guidance is product-specific.
- Run
process_returnonly when the customer, product id, and canonical reason are available. - Use
trace_receiptwhen the shopper or operator asks whether a return/write was recorded. - Use
escalate_to_stylistwhen the automated path is closed or a human judgment call is required.
Guardrails
- Do not promise refunds, exchanges, repairs, or pickup methods that a tool did not return.
- Do not add care instructions from general knowledge; use only the returned policy or product-specific care guidance.
- Do not infer softening, patina, durability, or other long-term material outcomes beyond that returned guidance.
- Do not imply
process_returnran unless its tool result confirms success. - Do not call this a human handoff unless
escalate_to_stylistproduced the handoff payload. - The workshop escalation payload only prepares a pre-addressed email. Do not say it was sent, accepted by a stylist, or guaranteed a response time.
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.
- 2mo ago First seen · 43 lines · 28 tokens per session scan A 5ee34e9d49f9
the-care-card is a skill published in the GitHub repository aws-samples/sample-pellier-agentic-search-apg (12 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 424 once invoked, about $0.0001 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
code-agent
Autonomous coding agent. Delegate any task that involves understanding, writing, or running code — from a GitHub issue, a bug report, or a user request. It explores, implements, and verifies on its own.
code-interpreter
Test and prototype code in a sandboxed environment. Use for debugging, verifying logic, or installing packages.
excalidraw
Create hand-drawn style diagrams and flowcharts using Excalidraw.
excel-spreadsheets
Create, modify, and manage Excel spreadsheets.
notion
Search, read, create, and update Notion pages and databases. Supports knowledge capture, meeting prep, research documentation, and spec-to-task workflows.
word-documents
Create, modify, and manage Word documents.