What is ir:agent-landscape?

A web-research workflow that tracks coding agents and tools that coordinate them, then ranks them by popularity and recent growth. It publishes the results as HTML pages, including a comparison report.

Use it to scan the coding-agent ecosystem, compare projects, record which agents a site already supports, and publish an agent landscape report.

It reduces the work of finding current agent projects and prevents unsupported claims by requiring each fact, such as GitHub stars or license, to come from a verifiable source.

How ingo-eichhorst/Irrlicht configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ingo-eichhorst/Irrlicht. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ingo-eichhorst/Irrlicht/main/.claude/skills/ir:agent-landscape/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ingo-eichhorst/Irrlicht

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-agent-landscape/github.svg)](https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-agent-landscape)

Your own site

<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-agent-landscape"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-agent-landscape/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-agent-landscape"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-agent-landscape.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 3,415 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.

Model	Per session	Once invoked
Fable 5.1	$0.00088	$0.03415
Opus 5	$0.00044	$0.01707
Sonnet 5	$0.00018	$0.00683
Haiku 4.5	$0.00009	$0.00342

Measured 9d ago against content hash b58aa072f204, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ir:agent-landscape 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.

The scan reads SKILL.md. This mod also ships 1 executable file (assets/generate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/ir:agent-landscape/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Landscape Tracker

Discover, track, and rank coding agents and agent orchestrators. Publish a styled HTML report to the irrlicht site at site/landscape/index.html and an in-depth comparison at site/landscape/compare/index.html.

Non-negotiable rules

Past runs of this skill invented data — fabricated star counts, wrong repo paths, copied descriptions instead of reading the actual README, and fake historical snapshots (e.g. "2026-01-01" entries for agents the skill only started tracking in April). Follow these rules to prevent a repeat:

Never invent a value. Every stars, language, license, description, funding_millions_usd, estimated_users, or historical snapshot must come from a concrete source you can quote (the gh CLI, a specific WebFetch URL, a specific search result). If you don't have a source, write null and move on.
Never copy an old value forward. If you can't re-verify a field on this run, set it to null instead of leaving whatever was in the file from last time.
Always use gh api for GitHub data, not WebFetch. gh api repos/OWNER/REPO returns canonical stars, language, license, description, archived flag, and follows renames. WebFetch on github.com returns JS-rendered pages that routinely give stale numbers.
Honor GitHub's repo-rename redirects. gh api returns a full_name field. If full_name != OWNER/REPO that you requested, the repo has been transferred. Update github_repo to the new canonical path in agent-data.json.
Never write a historical snapshot you didn't measure. stars_history may only contain entries this skill actually measured. Do not back-fill "~3 months ago" or "~1 month ago" rows from memory or estimate.
Plausibility check before writing. Before writing a new stars value, compare to the prior snapshot. If the delta is >30% in <30 days for a repo with >5k stars, investigate before trusting it — it's more likely a bad query than real growth. Common causes: cached HTML, wrong repo, joke repo inflating itself via README marketing.
Descriptions come from the repo's own description field, not from product marketing pages. If a description contains attribution (e.g. "Anthropic's X" or "Google's Y"), verify the GitHub owner matches the claim. badlogic/pi-mono is not Anthropic's. block/goose is not Block's anymore (it was transferred). cursor/cursor is not the editor source (it's the issue tracker).
Archived repos go in the "archived" list, not the ranked table. gh api returns archived: true — respect it.
Short-window growth is not 1-month or 3-month growth. Until the repo has a snapshot ≥30 days old, the growth column must read "Recent growth since (Nd ago)", not "1M" or "3M". The HTML generator already enforces this.

Read the full file on GitHub · 209 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

9d ago First seen · 209 lines · 88 tokens per session scan A b58aa072f204

Subscribe to this mod's changes

ir:agent-landscape is a skill published in the GitHub repository ingo-eichhorst/Irrlicht (97 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 3,415 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 2026-08-30.

Analytics and metrics Research

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

Irrlicht: Skill for Claude Code