agentcore-patterns

This skill should be used when an automated agent's output is published under its own identity and carries weight in someone else's work, such as a reviewer whose verdict lands on a pull request, and the open question is how much authority it has actually earned. Covers which conclusions such an agent may state as…

Skill for Claude CodeCodex

Part of the aws-startups-solution-architecture plugin — 2 skills shipped together

Install

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.

agentmods
npx agentmods add skills/awslabs/startups/agentcore-patterns
Any agent
npx skills add awslabs/startups --skill agentcore-patterns
Clone the repo
git clone --depth 1 https://github.com/awslabs/startups

Made for: Claude Code, Codex.

Or install aws-startups-solution-architecture, the plugin that ships this one along with the rest of its 2 skills.

Per session 198 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00198 $0.00806
Opus 5 $0.00099 $0.00403
Sonnet 5 $0.00040 $0.00161
Haiku 4.5 $0.00020 $0.00081

Measured today against content hash 27021bddeb3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentcore-patterns 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 today.

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.

solution-architecture/plugins/aws-startups-solution-architecture/skills/agentcore-patterns/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentCore Patterns

Apply these patterns to agents that act inside an engineering pipeline rather than serving end users. Upstream aws-agents owns the build, deploy, and hardening mechanics. What it does not cover is the judgment layer, which is where these agents actually fail.

Treat one constraint as primary: nobody is available to babysit the agent. A judge that is wrong, slow, or noisy will not be tuned over a quarter by a platform team. It gets ignored, and then it is worse than nothing, because it occupies the slot where review attention used to be.

Design for that outcome. Measure stability before granting an agent authority to block, report a stance on every axis so silence is never ambiguous, and compute in code anything the judgment depends on.

Reference files

  • references/git-code-reviewer-agent.md: Read before letting any agent's output carry weight in someone else's work. End-to-end wiring for a pull-request reviewer, from the credential identity that decides whether a verdict can be recorded at all, through reading the pull request as data, the trigger that reaches a credentialed runtime, what the agent should remember between runs, and the judgment design that decides whether anyone keeps reading the output. Written as field notes, including the failures.

Upstream skills to defer to

Do not restate the mechanics these own. Invoke them directly:

  • Skill("aws-agents:agents-build"): Agent construction, tools, prompts, memory, and multi-agent composition.
  • Skill("aws-agents:agents-deploy"): Container contract, deployment, versioning, rollback, and deploy-failure diagnosis.
  • Skill("aws-agents:agents-harden"): IAM scoping, inbound auth, secret handling, session lifecycle, and quotas.
  • Skill("aws-agents:agents-debug"): Traces, logs, and diagnosis of a deployed agent.
  • Skill("aws-agents:agents-optimize"): Evaluators, online monitoring, CI/CD quality gates, observability, and latency and token-cost tuning. Read this first if the goal is to measure an agent's quality. It owns the evaluator and quality-gate machinery; this skill covers only the narrower case where the agent is the gate, and the question is whether its verdicts are stable enough to carry authority.
  • Skill("aws-core:amazon-bedrock"): Model invocation, prompt caching, and throttling diagnosis.
  • Skill("aws-core:aws-ai-ml"): Model selection and inference-cost comparison.

Read the full file on GitHub · 40 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. today First seen · 40 lines · 198 tokens per session scan A 27021bddeb3d

Subscribe to this mod's changes

agentcore-patterns is a skill published in the GitHub repository awslabs/startups (16 stars, last pushed yesterday), licensed Apache-2.0. It adds 198 tokens to every session and 806 once invoked, about $0.0010 per session on Opus 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 2026-09-02.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens