Skip to content
anyai.fyi

agents-harden

Skill from aws/agent-toolkit-for-aws

Install

npx skills add aws/agent-toolkit-for-aws --skill agents-harden

Runs the open skills CLI and installs the skill for your agent (Claude Code, Codex, Cursor …). Alternatively copy the skill folder into .claude/skills/ or upload it in Claude.ai under Settings → Skills.

As a Claude Code plugin

/plugin marketplace add anthropics/claude-plugins-official /plugin install aws-agents@agent-toolkit-for-aws

This skill is part of the plugin “aws-agents”. In Claude Code the plugin installs it together with the plugin’s other skills, commands and hooks.

What does the agents-harden skill do?

Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance. Triggers on: "production checklist", "harden agent", "production ready", "secure agent", "inbound auth", "going live", "cold start optimization", "session lifecycle", "StopRuntimeSession", "quota", "throttling", "maxVms", "rate limit", "security audit of outbound API calls", "gateway target audit for production", "restrict who can call", "lock down endpoint", "only our app can call". Not for Cedar tool-restriction policies — use agents-connect. Not for quality measurement — use agents-optimize. Not for outbound credential storage or API key wiring — use agents-connect. Not for A2A agent-to-agent auth — use agents-build. Cold start observation and diagnosis (not optimization) routes to agents-debug.

Description from the SKILL.md in the source repository.

Questions about agents-harden

What does the agents-harden skill do?

Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance. Triggers on: "production checklist", "harden agent", "production ready", "secure agent", "inbound auth", "going live", "cold start optimization", "session lifecycle", "StopRuntimeSession", "quota", "throttling", "maxVms", "rate limit", "security audit of outbound API calls", "gateway target audit for production", "restrict who can call", "lock down endpoint", "only our app can call". Not for Cedar tool-restriction policies — use agents-connect. Not for quality measurement — use agents-optimize. Not for outbound credential storage or API key wiring — use agents-connect. Not for A2A agent-to-agent auth — use agents-build. Cold start observation and diagnosis (not optimization) routes to agents-debug.

How do I install agents-harden?

In a terminal: npx skills add aws/agent-toolkit-for-aws --skill agents-harden. The skills CLI asks which agents to install it for. In Claude.ai you can upload the skill folder as a ZIP under Settings → Skills.

Which agents can use agents-harden?

Skills use the open SKILL.md format, which Claude Code, Claude.ai, the Claude API, OpenAI Codex, Cursor, Gemini CLI and other agents support.

Is agents-harden safe to use?

Our automatic check found patterns worth a look (see “Check”). That is not proof of anything bad – read the SKILL.md and scripts before installing.

More skills from aws/agent-toolkit-for-aws

troubleshooting-aws-device-farm-runs
aws/agent-toolkit-for-aws

Diagnoses failed, errored, or skipped AWS Device Farm mobile app test runs on Android and iOS devices (runs, jobs, suites, tests, and their uploads) from their status, result messages, and artifacts (test …

Testing & QA curated
Risky patterns
setting-up-workspaces-applications
aws/agent-toolkit-for-aws

Provisions Amazon WorkSpaces Applications (AppStream 2.0) environments, from images and image builders to fleets and stacks, through a guided flow, for an AI agent or for human users.

DevOps & Cloud curated
No risky patterns found
render-to-aws
aws/agent-toolkit-for-aws

Migrate Render workloads to AWS through consented read-only discovery, mandatory clarification, architecture design, cost estimation, an optional what-if workshop, and opt-in artifact generation.

DevOps & Cloud curated
No risky patterns found
managing-glue-jobs
aws/agent-toolkit-for-aws

Guides AWS Glue customers through automatic version upgrades (auto upgrade, GlueVersion = auto) for Spark ETL jobs, step by step as the AWS Glue user guide describes: assess jobs, confirm they are …

DevOps & Cloud curated
No risky patterns found
aws-emulator
aws/agent-toolkit-for-aws

Installs, starts and troubleshoots AWS Emulator, the local emulator of AWS service APIs, and checks whether a project or a single operation works on the installed build.

DevOps & Cloud curated
Worth a look
deploying-containers-to-amazon-lightsail
aws/agent-toolkit-for-aws

Deploys, hosts, or runs a container or Docker app on Amazon Lightsail Container Service and returns a live, managed HTTPS URL at a flat monthly price — no cluster, VPC, load balancer …

DevOps & Cloud curated
No risky patterns found
aws-amplify
aws/agent-toolkit-for-aws

Build and deploy full-stack web and mobile apps with AWS Amplify Gen2 (TypeScript code-first). Covers auth (Cognito), data (AppSync/DynamoDB), storage (S3), functions, APIs, and AI (Amplify AI Kit with Bedrock).

Frontend & UI curated
No risky patterns found
querying-aws-sagemaker-catalog
aws/agent-toolkit-for-aws

Runs SQL analytics on SageMaker Catalog asset metadata tables exported as Apache Iceberg in S3 Tables. Covers governance queries, asset growth tracking, ownership audits, time-travel over catalog state, and metadata quality analysis. …

Data & Databases curated
No risky patterns found

Related skills in Security

azure-compliance
microsoft/azure-skills

Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks.

Security 715k installs curated
No risky patterns found
entra-app-registration
microsoft/azure-skills

Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal …

Security 714k installs curated
No risky patterns found
minimal-run-and-audit
lllllllama/rigorpilot-skills

Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and …

Security 499k installs
No risky patterns found
seo-audit
coreyhaines31/marketingskills

When the user wants to audit or diagnose SEO, or asks why traffic dropped, a page won't rank, or whether a setup like canonicals, hreflang, or redirects is right: technical SEO, indexing …

Security 257k installs
No risky patterns found
firebase-security-rules-auditor
firebase/agent-skills

Audits Firebase (Firestore, Cloud Storage) security rules for vulnerabilities, privilege escalation, role bypasses, create vs update inconsistencies, resource exhaustion, type safety, size limits, and hasOnly ownership checks.

Security 150k installs
No risky patterns found
landing-page-conversion-audit
autonnel/autonnel-skills

Audit a landing page, sales page or checkout page for conversion leaks and return a fix list ordered by expected revenue impact.

Security 131k installs
No risky patterns found
web-perf
cloudflare/skills

Audit, diagnose, or optimize website loading and interaction performance, Core Web Vitals, and Lighthouse performance scores.

Security 130k installs curated
No risky patterns found
browser-fingerprint-audit
liarjsdev/liarjs-skills

Audit a browser fingerprint for internal contradictions with the liarjs CLI - canvas, WebGL, WebGL2, WebGPU, audio, 220 fonts, WebRTC and timezone probes, scored against the TLS/HTTP/ASN view of the same request. …

Security 127k installs
No risky patterns found