agents-pay

Use when THIS agent needs to pay for x402-protected content at runtime: hitting a paywall mid-task, settling it via AgentCore Payments, and applying operator-defined spend limits. Covers payment setup, policy, session budgets, and troubleshooting. Triggers on: "my agent hit a 402 while calling an API", "a tool call returned 402 Payment Required", "my agent needs to pay for x402-protected content", "let the agent pay for content, capped at $5 per session", "set a spend limit for the agent", "ProcessPayment failed", or "why did my agent refuse to pay". Not for BUILDING payment capability for end users, including wallets and framework middleware; use agents-build and references/payments.md. For non-paid APIs via Gateway use agents-connect. For inbound auth use agents-harden. For project scaffolding use agents-get-started.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

85%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, well-sequenced with validation checkpoints, and uses clean one-level-deep progressive disclosure. Its main weakness is conciseness: the central security thesis is restated several times and the body (~525 lines) could be trimmed without losing clarity.

Suggestions

Consolidate the repeated 'the decision is in code, not the model' argument into one section and have other sections back-reference it rather than restating it (e.g. 'Read this before deploying', 'How the policy is honored across platforms', and 'Cross-runtime notes' overlap heavily).

Trim the cross-platform honesty table in 'How the policy is honored across platforms' — several rows restate the same gate-in-code point and could fold into the two genuinely platform-dependent bullets that follow.

The comparison table under 'Not this skill' duplicates the 'Do NOT use for' list below it; pick one form (table or list) for the boundary guidance to reduce token cost.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept filler, but the security 'one idea' (a payment decision is made in code, not by the model) is restated across 'The one idea that matters', 'Read this before deploying', 'How the policy is honored across platforms', and 'Cross-runtime notes', and could be tightened without losing the argument.	3 / 5
Actionability	Fully executable guidance throughout: copy-paste shell commands (init-config, new-session, x402_fetch_cli.py), an executable browser-handle Python snippet, a config-key-to-flag table, and documented exit codes covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced Step 0–6 process with an explicit validation gate (test_x402_policy.py must pass before a real endpoint), a preflight check, and a feedback loop for refusals (report and stop; do not retry unchanged).	5 / 5
Progressive Disclosure	The body is an overview with a Files table pointing to five real references and five real scripts (all verified present), each one level deep, well-signaled via markdown links and per-file role descriptions, with bulk detail deferred to references/.	5 / 5
	Total	18 / 20 Passed

Description

95%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 strong: it states concrete capabilities, provides natural trigger phrases, covers both what and when, and draws clear boundaries against related skills. The only sub-max dimension is specificity, which lists several actions but is not an exhaustive concrete-action inventory.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('hitting a paywall mid-task, settling it via AgentCore Payments, and applying operator-defined spend limits', 'payment setup, policy, session budgets, and troubleshooting'), with only minor coverage gaps keeping it below the comprehensive 5-anchor list.	4 / 5
Completeness	Explicitly answers both what (pay for x402-protected content at runtime, settle paywalls, apply spend limits) and when (a 'Use when...' lead plus a 'Triggers on:' list of concrete phrases), matching the 5-anchor example.	5 / 5
Trigger Term Quality	Includes comprehensive natural trigger phrases a user would actually say — 'my agent hit a 402 while calling an API', '402 Payment Required', 'set a spend limit for the agent', 'ProcessPayment failed', 'why did my agent refuse to pay' — covering synonyms and error strings.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (runtime agent self-payment) and explicitly disambiguates from sibling skills (agents-build, agents-connect, agents-harden, agents-get-started) with boundary lines, minimizing wrong-skill triggering.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (549 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: aws/agent-toolkit-for-aws
Path: plugins/aws-agents/skills/agents-pay/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.