Amazon Bedrock AgentCore Samples is a collection of examples and tutorials for deploying and operating AI agents with Amazon Bedrock AgentCore. Developers use it to integrate agent applications built with different frameworks and language models while learning AgentCore features. The catalogue add-ons provide agent-oriented guidance for working with these samples and services.
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 awslabs/agentcore-samples --skill multi-quarter-trend-analysisgit clone --depth 1 https://github.com/awslabs/agentcore-samplesWrote 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/awslabs/agentcore-samples/multi-quarter-trend-analysis)<a href="https://agentmods.dev/skills/awslabs/agentcore-samples/multi-quarter-trend-analysis"><img src="https://agentmods.dev/badge/skills/awslabs/agentcore-samples/multi-quarter-trend-analysis/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/awslabs/agentcore-samples/multi-quarter-trend-analysis"><img src="https://agentmods.dev/badge/skills/awslabs/agentcore-samples/multi-quarter-trend-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.01106 |
| Opus 5.5 | $0.00033 | $0.00442 |
| Sonnet 5.5 | $0.00016 | $0.00221 |
| Haiku 4.5 | $0.00008 | $0.00111 |
Grade A, and why
multi-quarter-trend-analysis 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Quarter Trend Analysis
Analyzes P&L data across all available quarters to identify directional trends and flag acceleration or deceleration in key financial metrics.
Prerequisites
No inputs required from the user — all data is fetched from the MCP server. Available quarters: Q1 2025, Q2 2025, Q3 2025, Q4 2024.
Steps
Step 1: Fetch all quarterly P&L data
Call get_financial_data for each quarter:
get_financial_data(period="Q4 2024")
get_financial_data(period="Q1 2025")
get_financial_data(period="Q2 2025")
get_financial_data(period="Q3 2025")
Store all four results. You now have a time series of: revenue, cogs, operating_expenses, ebitda.
Step 2: Fetch benchmark thresholds
get_kpi_benchmarks()
Store the formulas and benchmarks for use in Step 4.
Step 3: Calculate derived metrics for each quarter
Use python_exec to compute the following for every quarter:
- Gross Margin % = (Revenue - COGS) / Revenue * 100
- EBITDA Margin % = EBITDA / Revenue * 100
- Operating Expense Ratio = Operating Expenses / Revenue * 100
- QoQ Revenue Growth % = (Current Revenue - Prior Revenue) / Prior Revenue * 100 (Q4 2024 has no prior quarter — mark as N/A)
Example:
quarters = {
"Q4 2024": {"revenue": 4000000, "cogs": 1800000, "opex": 1000000, "ebitda": 1200000},
"Q1 2025": {"revenue": 3500000, "cogs": 1575000, "opex": 910000, "ebitda": 1015000},
"Q2 2025": {"revenue": 3800000, "cogs": 1710000, "opex": 980000, "ebitda": 1110000},
"Q3 2025": {"revenue": 4200000, "cogs": 1890000, "opex": 1050000, "ebitda": 1260000},
}
order = ["Q4 2024", "Q1 2025", "Q2 2025", "Q3 2025"]
results = {}
for i, q in enumerate(order):
d = quarters[q]
gm = round((d["revenue"] - d["cogs"]) / d["revenue"] * 100, 1)
em = round(d["ebitda"] / d["revenue"] * 100, 1)
opex_r = round(d["opex"] / d["revenue"] * 100, 1)
if i > 0:
prev_rev = quarters[order[i-1]]["revenue"]
qoq = round((d["revenue"] - prev_rev) / prev_rev * 100, 1)
else:
qoq = None
results[q] = {"gross_margin": gm, "ebitda_margin": em, "opex_ratio": opex_r, "qoq_growth": qoq}
print(f"{q}: GM={gm}% EBITDA={em}% OpEx={opex_r}% QoQ={qoq}%")
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 · 103 lines · 82 tokens per session scan A a4d19ec44ef5
multi-quarter-trend-analysis is a skill published in the GitHub repository awslabs/agentcore-samples (3,474 stars, last pushed yesterday), licensed Apache-2.0. It adds 82 tokens to every session and 1,106 once invoked, about $0.0003 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
travel-expense-audit
A travel-expense review workflow that checks reimbursement claims against policy handbooks and rate tables. It covers items such as hotel, transport, and daily meal allowances.
risk-scoring
Score how concentrated and risky a portfolio is on a 0-100 scale from its position weights. Use when the user asks how risky their portfolio is, whether it is too concentrated, or for a diversification check.
kirocrew-app-dev
Build, package, and publish Kiro Crew external apps. Covers app.json manifests, UI components, crons, skills, lifecycle hooks, development mode, registry publishing, and common pitfalls.
goal-conductor
Own a goal too large for one session ('clear the flaky-test backlog', 'push N PRs green') end to end via the work ledger — decompose into items, one session per item, read worker status as data, verify claims with the acceptance evaluator, decide each round until done. Use when handed such a goal.
computer-use
Read and drive native desktop apps through the accessibility layer — list apps, snapshot a window as a numbered element tree, then click/type/scroll/drag by element index or screen coordinates. Use for a desktop app, not a web page. macOS + Windows; off unless enabled in Settings.
security-conductor
Operating procedure for the kirocrew-security-conductor agent. Use when a security conductor session is seeded, inspected or debugged. Run vulnerability discovery on one target as a supervised fleet — one auditor per attack surface, an independent verifier per finding, two human gates.