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 ihatesea69/kiro-kit --skill bedrock-agentcoregit clone --depth 1 https://github.com/ihatesea69/kiro-kitWrote 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/ihatesea69/kiro-kit/bedrock-agentcore)<a href="https://agentmods.dev/skills/ihatesea69/kiro-kit/bedrock-agentcore"><img src="https://agentmods.dev/badge/skills/ihatesea69/kiro-kit/bedrock-agentcore/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/ihatesea69/kiro-kit/bedrock-agentcore"><img src="https://agentmods.dev/badge/skills/ihatesea69/kiro-kit/bedrock-agentcore.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 | $0.00063 | $0.01535 |
| Opus 5.5 | $0.00025 | $0.00614 |
| Sonnet 5.5 | $0.00013 | $0.00307 |
| Haiku 4.5 | $0.00006 | $0.00153 |
Grade A, and why
bedrock-agentcore 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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amazon Bedrock AgentCore
Activate this skill when deploying an agent to AWS or wiring AgentCore components together.
When to Use
- Containerising a Strands / LangGraph / CrewAI / LlamaIndex / ADK agent for hosting
- Choosing a deployment target for an agent (Harness vs Runtime vs Lambda)
- Adding session or long-term memory to a chatbot
- Wiring agent tracing, metrics, and logs
- Hosting an MCP server on AgentCore Runtime
Component Map
| Component | Purpose |
|---|---|
| Runtime | Serverless deployment of an agent container |
| Gateway | Turns APIs, Lambdas, and services into MCP tools (see agentcore-gateway-mcp) |
| Memory | Short-term session context, long-term records |
| Identity | Access control for agents and callers |
| Observability | Traces, metrics, logs for agent runs |
| Code Interpreter | Sandboxed code execution as a tool |
| Browser tool | Headless browsing as a tool |
AgentCore was in preview from July 2025 and reached GA in October 2025 across
nine regions (us-east-1, us-west-2, eu-central-1, ap-southeast-1,
ap-northeast-1 among them). Do not assert that every component is GA —
component availability moves. Check the
release notes
and cite the date you checked.
Choosing a Target
AgentCore Harness (GA June 2026) — no infrastructure, no container, no
orchestration loop. You call CreateHarness and then InvokeHarness. Model
providers include Bedrock, Anthropic, OpenAI, and Gemini. Use it when a hosted
model plus tools is genuinely enough.
AgentCore Runtime — you have agent code and want it hosted. Deliberately framework-agnostic: CrewAI, LangGraph, LlamaIndex, Google ADK, the OpenAI Agents SDK, and Strands Agents all run on it, with any FM in or out of Bedrock (OpenAI, Gemini, Claude, Amazon Nova, Llama, Mistral), speaking MCP and A2A.
Plain Lambda + InvokeModel — it is not really an agent. One model call with
fixed post-processing does not need an agent runtime.
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 · 167 lines · 63 tokens per session scan A dcacee24b9bc
bedrock-agentcore is a skill published in the GitHub repository ihatesea69/kiro-kit (19 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 1,535 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 2026-09-03.
bedrock-agentcore compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bedrock-agentcoreihatesea69/kiro-kit | Skill | 19 | 2mo ago | MIT | A | 63 | Claude Code, Codex |
| author-labelsvercel/vercel | Skill | 17k | 3d ago | Apache-2.0 | A | 25 | Claude Code, Codex |
| claw-adminx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 48 | Claude Code, Codex |
| x-netsx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 69 | Claude Code, Codex |
| x-themex-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 74 | Claude Code, Codex |
| x-arpx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 64 | Claude Code, Codex |
| x-osvx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 72 | Claude Code, Codex |