agentmods.dev

kiro-web-search AGENTS.md

kiro-web-search AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from vokako/kiro-web-search. It costs 1,017 tokens per session, scanned A, original, MIT.

Project-specific instructions for Kiro Web Search, a small server that connects coding agents to Kiro's web-search service. It explains the project structure, architecture, configuration, and conventions.

In plain words
What is it for?
It is for guiding work on the Python MCP server, its plugin files, authentication setup, and related documentation.
Why use it?
It gives coding agents the context needed to change this repository without misunderstanding how its adapter works.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

not rated 4 1mo ago A scan 1,017 tokens original MIT
View the source file vokako/kiro-web-search pypi.org
Install

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.

agentmods
npx agentmods add instructions/vokako/kiro-web-search/agents-md
Clone the repo
git clone --depth 1 https://github.com/vokako/kiro-web-search

Made for: Claude Code, Codex, OpenCode.

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-web-search AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vokako/kiro-web-search/agents-md.svg)](https://agentmods.dev/instructions/vokako/kiro-web-search/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/vokako/kiro-web-search/agents-md"><img src="https://agentmods.dev/badge/instructions/vokako/kiro-web-search/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,017 This file is loaded in full into every session.
When invoked 1,017 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.01017 $0.01017
Opus 5 $0.00508 $0.00508
Sonnet 5 $0.00203 $0.00203
Haiku 4.5 $0.00102 $0.00102

Measured 6d ago against content hash 81a44261efd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

kiro-web-search AGENTS.md scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

4. **stdlib only for HTTP.** `urllib` is enough. Don't add `httpx`/`requests`
AGENTS.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Agent-facing entry point. For user-facing info see README.md.

What this project is

A single-tool MCP server that wraps Kiro's backend web_search endpoint. The upstream is itself an MCP server reachable via AmazonCodeWhispererStreamingService.InvokeMCP on runtime.us-east-1.kiro.dev, so this project is fundamentally a transport adapter: stdio JSON-RPC ↔ HTTPS + Bearer auth.

Keep it thin. Any temptation to "enrich" or "post-process" results should be resisted — see docs/design-docs/features/web-search-mcp.md for the reasoning.

Architecture one-liner

MCP client ──stdio JSON-RPC──▶ FastMCP (this pkg) ──HTTPS Bearer──▶ Kiro backend MCP

Code map

  • src/kiro_web_search/server.py — everything lives here: config resolution, HTTP call to upstream, FastMCP tool definition, CLI entry point.
  • src/kiro_web_search/__main__.py — enables python -m kiro_web_search.
  • .claude-plugin/marketplace.json — makes this repo a Claude Code plugin marketplace. Users add via /plugin marketplace add vokako/kiro-web-search.
  • .claude-plugin/plugin.json — plugin manifest. Declares userConfig.api_key (prompted at install time, stored in the system keychain) and embeds the MCP server config inline. Substitution: KIRO_API_KEY=${user_config.api_key}.
  • .agents/plugins/marketplace.json — Codex plugin marketplace. Users add via codex plugin marketplace add vokako/kiro-web-search. Local plugin source must be a subdir (./plugins/...); Codex rejects "./", so the Codex plugin cannot live at the repo root like the Claude one does.
  • plugins/kiro-web-search/.codex-plugin/plugin.json — Codex plugin manifest. Unlike Claude, mcpServers is a path to a file, not an inline object, and there is no userConfig secret prompt.
  • plugins/kiro-web-search/.mcp.json — Codex MCP server file. The API key is inherited from the shell via env_vars: ["KIRO_API_KEY"] (Codex can't prompt for it). Format verified against openai/codex core-plugins/src/loader.rs.
  • tests/ — smoke tests for the handshake + a mocked tools/call.

Read the full file on GitHub · 85 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. 6d ago First seen · 85 lines · 1,017 tokens per session scan A 81a44261efd7

Subscribe to this mod's changes

kiro-web-search AGENTS.md is an instructions file published in the GitHub repository vokako/kiro-web-search (4 stars, last pushed 1mo ago), licensed MIT. It adds 1,017 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens