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 governed-postgres-agentgit 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/governed-postgres-agent)<a href="https://agentmods.dev/skills/aws-samples/sample-pellier-agentic-search-apg/governed-postgres-agent"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-pellier-agentic-search-apg/governed-postgres-agent/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/governed-postgres-agent"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-pellier-agentic-search-apg/governed-postgres-agent.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 | $0.00046 | $0.00987 |
| Opus 5.5 | $0.00018 | $0.00395 |
| Sonnet 5.5 | $0.00009 | $0.00197 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
governed-postgres-agent 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Can this agent read or change something it should not?
Review one tool against the applicable database contracts from DAT416. An agent selects tools and proposes arguments; the application implements their SQL and controls their authority. Establish what those controls enforce.
Key takeaway: An agent's answer is a claim. Permissions, identity, database behavior and retry behavior determine what it can actually do.
Start with the requested tool
Identify the tool, its caller and the operation under review. Trace its arguments through the implementation to the SQL, database role and returned result. Follow wrappers and alternative entry points when they affect that operation. Cite file paths and lines. If the entry point is unclear, locate likely candidates before asking one focused question.
Keep the review within the user's request. Default to source inspection and a proposed test plan. Do not edit files, create approvals, deploy, or execute database writes unless authorized. Database probes that write or change policies belong in an explicitly selected disposable test environment. Rollback does not undo every possible external trigger side effect.
Select the contracts that apply
| Contract | Question | Read when relevant |
|---|---|---|
| 1. Preserve requirements | Can retrieval or a retry lose the caller's hard constraints? | Retrieval |
| 2. Ground bounded answers | Does the tool preserve authoritative facts, missing records and errors? | Tool results |
| 3. Bind identity and ownership | Can proposed arguments change whose records are accessed? | Identity and RLS |
| 4. Authorize and deduplicate writes | Can execution bypass the approved scope or repeat a business effect? | Writes |
A stock lookup may need contracts 1 and 2; a customer ticket read needs 2 and 3; a reimbursement needs 3 and 4. Explain exclusions. Pellier's human approval, RRF configuration, role layout and AgentCore services are examples, not requirements for every application. Establish the application's intended authorization and business rules before judging its implementation.
What ships with it
10 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.
- examples/expense-review.md 4.1 KB
- examples/expense-review.sql 1.5 KB
- examples/setup.sql 7.2 KB
- README.md 3.4 KB
- references/01-filter-before-ranking.md 3.7 KB
- references/02-bounded-facts.md 3.0 KB
- references/03-bind-identity-enforce-ownership.md 4.0 KB
- references/04-approve-and-deduplicate-writes.md 5.0 KB
- references/mcp-publishing.md 2.4 KB
- references/proof-queries.sql 7.5 KB
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.
- 2d ago First seen · 89 lines · 46 tokens per session scan A 6f9c1776dd3f
governed-postgres-agent is a skill published in the GitHub repository aws-samples/sample-pellier-agentic-search-apg (12 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 987 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 2026-11-02.
Other skills, from other repositories
postgres
Read Postgres as compact YAML through bin/postgres/query.go (read-only guard, named profiles). Use when a task needs table contents, column types, or a SELECT against an ops database.
alloydb-basics
Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB Model Context Protocol (MCP) tools for automated database operations. Use when creating, configuring, or administering AlloyDB databases. Do NOT use for general PostgreSQL instances (e.g. Cloud SQL) or other GCP databases.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
db-repair
Auto-fix gbrain's Postgres access so the brain stays available. When any gbrain command or MCP tool result carries a GBRAINDBACCESS marker (or an operator reports the brain database is down), run the hardcoded gbrain db-repair ladder: diagnose, apply the safe tier, verify. The action is ALWAYS the hardcoded command …
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…