agentmods.dev

arwp-agent-discovery

arwp-agent-discovery is a skill for Claude Code, Codex from dkharlanau/agent-ready-web-profile. It costs 88 tokens per session (772 once invoked), scanned A, original, Apache-2.0.

A skill for making a website easier for software agents to find and use. It checks the site's real interfaces and adds or documents machine-readable surfaces such as API descriptions, agent instructions, and navigation files.

In plain words
What is it for?
Use it to inspect and improve agent discovery, API catalogs, sitemaps, agent instructions, and connections to agent protocols.
Why use it?
It prevents documentation from claiming support for protocols or tools that the website does not actually implement.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

not rated 0repo yesterday A scan 88 tokens original Apache-2.0

Good fit Use it to inspect and improve agent discovery, API catalogs, sitemaps, agent instructions, and connections to agent protocols.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dkharlanau/agent-ready-web-profile/arwp-agent-discovery
View source ↗ dkharlanau/agent-ready-web-profile dkharlanau.github.io
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.

Any agent
npx skills add dkharlanau/agent-ready-web-profile --skill arwp-agent-discovery
Clone the repo
git clone --depth 1 https://github.com/dkharlanau/agent-ready-web-profile

Made for: Claude Code, Codex.

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 arwp-agent-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-agent-discovery/github.svg)](https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-agent-discovery)
Your own site
<a href="https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-agent-discovery"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-agent-discovery/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 arwp-agent-discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-agent-discovery"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-agent-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 772 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 $0.00088 $0.00772
Opus 5 $0.00044 $0.00386
Sonnet 5 $0.00018 $0.00154
Haiku 4.5 $0.00009 $0.00077

Measured 4d ago against content hash 5e4d8c0784ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

arwp-agent-discovery 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 4d 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.

skills/arwp-agent-discovery/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ARWP Agent Discovery

Use this skill to make a website easier for agents to discover and operate without inventing a competing protocol or fake capability.

Decision order

Prefer existing upstream mechanisms before adding ARWP-native metadata:

  1. ordinary semantic HTML and stable canonical URLs;
  2. OpenAPI / RFC API Catalog where real APIs exist;
  3. Agent Skills for reusable procedures;
  4. A2A Agent Card for real agent endpoints;
  5. MCP metadata/runtime for actual MCP servers;
  6. WebMCP only for real browser-exposed tools;
  7. ARD for agentic-resource discovery when appropriate;
  8. ARWP publisher profile as an optional service map tying real surfaces together.

Workflow

  1. Inventory actual interfaces.

    • Search code/config for API routes, OpenAPI, MCP, A2A, skills, WebMCP, feeds, search endpoints, data exports and auth metadata.
    • Distinguish documentation mentioning a protocol from an implemented capability.

  2. Add lightweight readability surfaces.

    • llms.txt: concise canonical routes/resources; do not duplicate the whole site.
    • AGENTS.md: repository instructions for coding agents when developer-facing.
    • sitemap.md: optional compact navigation map.
    • Preserve normal XML sitemap/canonical SEO independently.

  3. Add Agent Skills for repeatable tasks.

    • Folder name is kebab-case.
    • File must be exactly SKILL.md.
    • Frontmatter must include name and trigger-rich description.
    • Keep the main skill concise and use references/, scripts/, or assets/ for progressive disclosure.
    • Skills should execute a real workflow, not merely restate documentation.

  4. Add structured discovery only where backed by implementation.

    • OpenAPI URLs must describe real endpoints.
    • A2A discovery URLs are metadata; do not treat a card URL as the callable endpoint unless the spec says so.
    • MCP server cards/metadata are evidence, not authorization.
    • ARD resources are discovery evidence; relevance is not trust.
    • Never expose internal/private endpoints in public discovery files.

Read the full file on GitHub · 74 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. 4d ago First seen · 74 lines · 88 tokens per session scan A 5e4d8c0784ec

Subscribe to this mod's changes

arwp-agent-discovery is a skill published in the GitHub repository dkharlanau/agent-ready-web-profile (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 772 once invoked, about $0.0004 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 2026-09-07.

Backend and APIsBuilding agentsa2aagent-skillsagentic-aiai-agentsllms-txtwebmcp
Related

Other skills, from other repositories

acp-checkout-rest

Implement the ACP REST checkout API — create, update, retrieve, complete, and cancel checkout sessions. Use when building merchant-side checkout endpoints, handling the checkout session state machine, or integrating with AI agent checkout flows.

OrcaQubits/agentic-commerce-skills-plugins · 49 tokens

a2a-client

Build an A2A client — the agent-side code that discovers other agents, sends tasks, handles responses, and manages multi-turn conversations. Use when implementing the client side that delegates work to A2A agents.

OrcaQubits/agentic-commerce-skills-plugins · 48 tokens

a2a-jsonrpc-transport

Implement the A2A JSON-RPC 2.0 transport layer — request/response format, method routing, batch requests, and HTTP details. Use when building custom A2A transport handling or debugging protocol-level issues.

OrcaQubits/agentic-commerce-skills-plugins · 53 tokens

a2a-mcp-bridge

Build bridges between A2A and MCP — wrap A2A agents as MCP tools, use MCP tools from A2A agents, and architect hybrid multi-agent systems. Use when integrating A2A agent-to-agent communication with MCP tool access.

OrcaQubits/agentic-commerce-skills-plugins · 57 tokens

a2a-server

Build an A2A server — the agent-side endpoint that receives JSON-RPC requests, processes tasks, manages state, and returns results. Use when implementing the server side of an A2A agent.

OrcaQubits/agentic-commerce-skills-plugins · 46 tokens

a2a-streaming

Implement A2A SSE streaming — message/stream method, Server-Sent Events, TaskStatusUpdateEvent, TaskArtifactUpdateEvent, and re-subscription. Use when building real-time streaming responses in A2A agents.

OrcaQubits/agentic-commerce-skills-plugins · 51 tokens