agentmods.dev

kiro-research

kiro-research is a skill for Claude Code from signalcompose/claude-tools. It costs 53 tokens per session (615 once invoked), scanned A, original, MIT.

A read-only research skill that asks Kiro CLI for answers about Amazon Web Services (AWS), the cloud platform, using its built-in knowledge rather than web searches.

In plain words
What is it for?
Use it for AWS documentation questions, CloudFormation or CDK troubleshooting, error investigation, and architecture or best-practice questions when Kiro CLI is installed.
Why use it?
It provides a focused way to investigate AWS errors, documentation questions, and design choices without changing cloud resources.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ask-kiro plugin — 1 skill shipped together

not rated 4repo 12d ago A scan 53 tokens original MIT

Good fit Use it for AWS documentation questions, CloudFormation or CDK troubleshooting, error investigation, and architecture or best-practice questions when Kiro CLI is installed.

Compare 6 skills from other repositories ↓
View source ↗ signalcompose/claude-tools
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add signalcompose/claude-tools
Claude Code
/plugin install ask-kiro

Made for: Claude Code.

Or install ask-kiro, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for kiro-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/signalcompose/claude-tools/kiro-research/github.svg)](https://agentmods.dev/skills/signalcompose/claude-tools/kiro-research)
Your own site
<a href="https://agentmods.dev/skills/signalcompose/claude-tools/kiro-research"><img src="https://agentmods.dev/badge/skills/signalcompose/claude-tools/kiro-research/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.

agentmods 80×15 button for kiro-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/signalcompose/claude-tools/kiro-research"><img src="https://agentmods.dev/badge/skills/signalcompose/claude-tools/kiro-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 615 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00053 $0.00615
Opus 5 $0.00026 $0.00308
Sonnet 5 $0.00011 $0.00123
Haiku 4.5 $0.00005 $0.00061

Measured 9d ago against content hash 23a5342ac31b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kiro-research 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 9d 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.

plugins/ask-kiro/skills/kiro-research/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kiro Research Skill

This skill provides integration with Kiro CLI for AWS research and troubleshooting tasks. Kiro runs in readonly mode - answering from its trained AWS expertise without web search.

Prerequisites

  • Kiro CLI installed (visit https://kiro.dev or download from AWS)
  • AWS credentials configured (for AWS-specific operations)

Available Scripts

All scripts are located in ${CLAUDE_PLUGIN_ROOT}/scripts/.

1. Check Installation

${CLAUDE_PLUGIN_ROOT}/scripts/check-kiro.sh

Verifies Kiro CLI is installed and accessible.

2. Research Mode (kiro-cli chat)

${CLAUDE_PLUGIN_ROOT}/scripts/kiro-ask.sh "your research question"

Use for:

  • AWS service documentation lookup
  • CloudFormation/CDK troubleshooting
  • AWS error investigation
  • Best practices inquiry
  • Architecture recommendations

Example:

${CLAUDE_PLUGIN_ROOT}/scripts/kiro-ask.sh "How do I configure VPC endpoints for S3?"

Workflow

  1. First, verify Kiro CLI is available using check-kiro.sh
  2. For research tasks, use kiro-ask.sh with the research prompt
  3. Summarize findings and provide actionable recommendations

Kiro CLI Options Reference

Option Description
--no-interactive Run without user input (used by scripts)
--agent <AGENT> Specify agent to use
--model <MODEL> Specify model to use
-a, --trust-all-tools Allows model to use any tool without confirmation
--trust-tools=<TOOL_NAMES> Trust only specific tools (e.g., --trust-tools=fs_read,fs_write)

Error Handling

  • Timeout: Commands timeout after 120 seconds
  • Not installed: Provides installation instructions
  • Credentials: Prompts to configure AWS credentials if needed

Input Sanitization

For security, prompts are sanitized before execution:

  • Newlines and carriage returns are removed (multi-line prompts become single-line)
  • Backticks (`) and dollar signs ($) are stripped to prevent prompt injection

Read the full file on GitHub · 86 lines

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. 9d ago First seen · 86 lines · 53 tokens per session scan A 23a5342ac31b

Subscribe to this mod's changes

kiro-research is a skill published in the GitHub repository signalcompose/claude-tools (4 stars, last pushed 12d ago), licensed MIT. It adds 53 tokens to every session and 615 once invoked, about $0.0003 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 2026-08-31.

Research
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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens