agents-harden

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.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and well-structured with strong section-level debugging workflows and real one-level-deep references. Its main weaknesses are minor verbosity in narrative intros and a large inline body that leans on a single reference file.

Suggestions

Trim narrative introductory paragraphs in the cold-start and session-lifecycle sections to just the actionable guidance, keeping conciseness closer to the lean anchor.

Move detailed session-lifecycle/maxVms triage or cold-start breakdown content into a dedicated reference file to reduce inline SKILL.md weight and strengthen progressive disclosure.

Add a single end-of-process validation gate (e.g., a 'verify readiness before deploy' step that re-runs agentcore status --json) to give the workflow a unifying checkpoint.

Dimension	Reasoning	Score
Conciseness	Dense, actionable, domain-specific content that does not explain concepts Claude already knows, but several narrative introductory paragraphs (e.g., cold-start and session-lifecycle openers) could be trimmed without losing clarity.	4 / 5
Actionability	Fully executable guidance throughout — concrete agentcore/aws CLI commands, copy-paste JSON policies, and complete Python examples (@requires_api_key, add_async_task, StopRuntimeSession) covering the common production cases.	5 / 5
Workflow Clarity	A numbered Process (Step 0–2) plus explicit ordered debugging workflows with feedback loops (JWT auth failure order, maxVms triage order), but the overall checklist lacks a single end-to-end validation gate.	4 / 5
Progressive Disclosure	Well-sectioned body with clearly signaled one-level-deep references (references/limits.md verified present, linked in context) and cross-skill links; the main SKILL.md is heavy with inline detail that a more aggressive split could offload.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and explicitly scopes what, when, and what-not-to-use-this-for. It is a strong, well-routed skill description with minimal overlap risk against sibling skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete production-hardening actions ("IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance"), giving comprehensive coverage rather than minor gaps.	5 / 5
Completeness	Explicitly answers both what (the action list) and when ("Use when preparing your agent for production" plus a "Triggers on:" clause and negative-scope routing), matching the anchor for clear concrete trigger guidance.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would say ("production checklist", "harden agent", "going live", "throttling", "maxVms", "rate limit", "lock down endpoint", "only our app can call"), including error-string synonyms.	5 / 5
Distinctiveness Conflict Risk	Tight AgentCore production-hardening niche with explicit negative-scope routing to four sibling skills (agents-connect, agents-optimize, agents-build, agents-debug), minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (705 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 5 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: aws/agent-toolkit-for-aws
Path: plugins/aws-agents/skills/agents-harden/SKILL.md
Commit: 68d9e85

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.