awslabs/agent-plugins is a collection of plugins, skills, instructions, an MCP server, a hook, and a setting that guide AI coding agents in architecting, deploying, and operating software on Amazon Web Services. It is for developers using coding agents such as Claude Code, Codex, and Cursor with AWS projects. The catalogue entries are the repository's own agent workflows and supporting components.
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/agent-plugins --skill api-gatewaygit clone --depth 1 https://github.com/awslabs/agent-pluginsWrote 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/agent-plugins/api-gateway)<a href="https://agentmods.dev/skills/awslabs/agent-plugins/api-gateway"><img src="https://agentmods.dev/badge/skills/awslabs/agent-plugins/api-gateway/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/agent-plugins/api-gateway"><img src="https://agentmods.dev/badge/skills/awslabs/agent-plugins/api-gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 140 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 140 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 142 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 153 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00108 | $0.03578 |
| Opus 5.5 | $0.00043 | $0.01431 |
| Sonnet 5.5 | $0.00022 | $0.00716 |
| Haiku 4.5 | $0.00011 | $0.00358 |
Grade A, and why
api-gateway 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amazon API Gateway Development
Expert guidance for building, managing, governing, and operating APIs with Amazon API Gateway. Covers REST APIs (v1), HTTP APIs (v2), and WebSocket APIs.
How to Use This Skill
When answering API Gateway questions:
- Read the relevant reference file(s) before responding, do not rely solely on this summary
- For tasks spanning multiple concerns (e.g., "private API with mTLS and custom domain"), read all relevant references
- When the user needs IaC templates, consult
references/sam-cloudformation.mdorreferences/sam-service-integrations.mdand provide complete, working SAM/CloudFormation YAML - Always mention relevant pitfalls and limits that affect the user's design
Quick Decision: Which API Type?
Choose the right API type first. This decision affects every downstream choice.
REST API is the full-featured API management platform for enterprises. It provides the governance, security, monetization, and operational controls that organizations need to build, publish, and manage APIs at scale, including usage plans with per-consumer throttling and quotas, API keys, request validation, WAF integration, resource policies, caching, canary deployments, and private endpoints.
HTTP API is the lightweight, low-cost proxy optimized for simpler API workloads. It offers ~70% lower cost and lower latency but trades away the API management features. Choose HTTP API when you need a fast, lightweight proxy to Lambda or HTTP backends and don't require the enterprise controls above.
| Factor | REST API (v1) | HTTP API (v2) | WebSocket API |
|---|---|---|---|
| Positioning | Full API management | Low-cost proxy | Real-time bidirectional |
| Cost | Higher | ~70% cheaper | Per-message pricing |
| Latency | Higher | Lower | Persistent connection |
| Max timeout | 50ms-29s (up to 300s Regional/Private) | 30s hard limit | 29s |
| Payload | 10 MB | 10 MB | 128 KB message / 32 KB frame |
| API Management | |||
| Usage plans/API keys | Yes | No | No |
| Request validation | Yes (JSON Schema draft 4) | No | No |
| Caching | Yes (0.5-237 GB) | No | No |
| Custom gateway responses | Yes | No | No |
| VTL mapping templates | Yes | No (parameter mapping only) | Yes |
| Security & Governance | |||
| WAF | Yes | No (use CloudFront + WAF) | No |
| Resource policies | Yes | No | No |
| Private endpoints | Yes | No | No |
| mTLS | Yes (Regional custom domain only) | Yes (Regional custom domain only) | Via CloudFront viewer mTLS |
| Auth | |||
| Lambda authorizer | Yes (TOKEN + REQUEST) | Yes (REQUEST only, simple + IAM policy format) | Yes (REQUEST on $connect only) |
| JWT authorizer | No (use Cognito authorizer) | Yes (native) | No |
| Cognito authorizer | Yes (native) | Use JWT authorizer | No |
| Operations | |||
| Canary deployments | Yes | No | No |
| Response streaming | Yes | No | No |
| X-Ray tracing | Yes | No | No |
| Execution logging | Yes | No | Yes |
| Custom domain sharing | Not with WebSocket | Not with WebSocket | Not with REST/HTTP |
What ships with it
18 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.
- references/architecture-patterns.md 19 KB
- references/authentication.md 9.4 KB
- references/custom-domains-routing.md 8.5 KB
- references/deployment.md 15 KB
- references/governance.md 9.8 KB
- references/observability-analytics.md 4.2 KB
- references/observability-logging.md 11 KB
- references/observability-metrics-alarms.md 5.5 KB
- references/performance-scaling.md 9.0 KB
- references/pitfalls.md 2.0 KB
- references/requirements-gathering.md 15 KB
- references/sam-cloudformation.md 7.8 KB
- references/sam-service-integrations.md 23 KB
- references/security.md 18 KB
- references/service-integrations.md 24 KB
- references/service-limits.md 11 KB
- references/troubleshooting.md 15 KB
- references/websocket.md 7.4 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.
- 1mo ago First seen · 207 lines · 108 tokens per session scan A c0971ab0e5e6
api-gateway is a skill published in the GitHub repository awslabs/agent-plugins (924 stars, last pushed 3d ago), licensed Apache-2.0. It adds 108 tokens to every session and 3,578 once invoked, about $0.0004 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
analytics-opensearch-expertise
Amazon OpenSearch Service domain health assessment. Performs read-only, API-driven checks against a customer's OpenSearch domain(s) covering cluster health, node/shard configuration, performance metrics, security posture, and cost optimization signals. Activate this skill for requests about OpenSearch or Elasticsearch…
database-rds-devops
Database-level data-plane diagnostics for Aurora MySQL and Aurora PostgreSQL. Executes predefined read-only health check queries via RDS Data API to analyze buffer pool, connections, locks, replication, storage, performance, and index efficiency. Requires the rds-aidba MCP server for database-internal access beyond…
storage-s3-resiliency-expertise
S3 resiliency, security, and data protection review. Assesses one or many S3 buckets across nine dimensions — versioning, replication, object lock, encryption, block public access, bucket policy, ownership controls, server access logging, and static website hosting — using read-only control-plane API calls, then…
crm-production-investigation-guidelines
Guidelines for investigating production incidents in the CRM application. Use when triaging any alert or incident involving the CRM REST API, SQS queues, Lambda functions, or Aurora DSQL database in this AWS account. Ensures thorough root cause analysis using AWS-native observability tools.
agentproto-llm-endpoint
Use the local LLM endpoint proxy (localhost:18090) — or your own gated public deployment — to route Claude Code / Claude SDK through custom providers (OpenRouter, Moonshot, Groq, ZAI) via an Anthropic-compatible gateway. Covers adapter-specific behaviors, auth patterns, proxy codenames, and common failure modes.
api-authentication
API authentication patterns including JWT, OAuth 2.0, API keys, and session-based auth. Covers token generation, validation, refresh strategies, security best practices, and when to use each pattern. Use when implementing API authentication, choosing auth strategy, securing endpoints, or debugging auth issues.…