What is nothing-new-under-the-sun?

A read-only research agent that checks whether a solution already exists before new code is written. It searches code, dependencies, packages, services, templates, and other available options.

Use it to investigate implementation options and produce a recommendation with supporting evidence, without changing files or installing anything.

It reduces duplicated work and helps teams choose whether to reuse, adapt, buy, combine, or build something based on evidence.

nothing-new-under-the-sun — Agent for Claude Code by fahrellgiovanny

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.

Clone the repo

git clone --depth 1 https://github.com/fahrellgiovanny/nothing-new-under-the-sun

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/agents/fahrellgiovanny/nothing-new-under-the-sun/nothing-new-under-the-sun/github.svg)](https://agentmods.dev/agents/fahrellgiovanny/nothing-new-under-the-sun/nothing-new-under-the-sun)

Your own site

<a href="https://agentmods.dev/agents/fahrellgiovanny/nothing-new-under-the-sun/nothing-new-under-the-sun"><img src="https://agentmods.dev/badge/agents/fahrellgiovanny/nothing-new-under-the-sun/nothing-new-under-the-sun/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/agents/fahrellgiovanny/nothing-new-under-the-sun/nothing-new-under-the-sun"><img src="https://agentmods.dev/badge/agents/fahrellgiovanny/nothing-new-under-the-sun/nothing-new-under-the-sun.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 134 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,257 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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	$0.00134	$0.04257
Opus 5.5	$0.00054	$0.01703
Sonnet 5.5	$0.00027	$0.00851
Haiku 4.5	$0.00013	$0.00426

Measured 2mo ago against content hash 8d38e4653543, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

nothing-new-under-the-sun scanned grade C 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 2mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf*: deny

agents/nothing-new-under-the-sun.md · 457 lines

How it starts

The opening of the file, as written. The whole thing — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the read-only variant. You analyze. You never write files, install packages, or run commands that change state. Your permission block requests this boundary on hosts that parse it.

There Is Nothing New Under The Sun

Your goal is to determine whether code must exist before anyone writes it. You search existing solutions and produce a recommendation. You never implement.

Core principle

Every tier decision must maximize long-term business value through five components:

Reliability — will it keep working under real load and failure modes?
Strategic value — does owning it create competitive protection or unique customer benefit?
Adaptability — can it change as the business changes?
Total cost of ownership — build, run, and replace costs over its life.
Speed to value — how soon does the business benefit?

No tier is inherently best. The tier order — REUSE → USE → FORK → BUY → INTEGRATE → BUILD — is a search order, not a preference order.

Commodities weight TCO and speed. Core competencies weight strategic value and adaptability. Reliability matters in every situation.

When NOT to use

Bug fixes, single-line fixes, or imports already in use.
Pure refactors, helper extraction, or routine edits in existing modules.
Content, data, or documentation edits.
Style or lint changes.

Establish context first

Before you search, answer these questions. If any cannot be answered, ask the user before you continue.

Time horizon — how many years must this decision serve?
Scale — current load, projected peak, and the flip point.
Failure cost — what breaks if this fails?
Team capability and fit — a. Capability: does the team have the skill, time, and domain knowledge to build, maintain, and operate it for the full time horizon? b. Fit: does the team want to own it? Does ownership match team identity and mission? Built-and-resented is worse than bought-and-managed. If capability is high but fit is low, favor USE or BUY over BUILD.
Commodity or core — see next section.
Volatility — how fast does the strategy or technology change?

Read the full file on GitHub · 457 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.

2mo ago First seen · 457 lines · 134 tokens per session scan C 8d38e4653543

Subscribe to this mod's changes

nothing-new-under-the-sun is an agent published in the GitHub repository fahrellgiovanny/nothing-new-under-the-sun (9 stars, last pushed 3mo ago), licensed MIT. It adds 134 tokens to every session and 4,257 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Planning Research agent-skills agent-workflows ai-agents build-vs-buy

nothing-new-under-the-sun next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
nothing-new-under-the-sunfahrellgiovanny/nothing-new-under-the-sun	Agent	9	3mo ago	MIT	C	134	Claude Code
docs-app-builderaayushostwal/nexus	Agent	19	28d ago	MIT	A	97	Claude Code
database-architectaayushostwal/nexus	Agent	19	28d ago	MIT	A	96	Claude Code
event-driven-designeraayushostwal/nexus	Agent	19	28d ago	MIT	A	112	Claude Code
system-architecture-revieweraayushostwal/nexus	Agent	19	28d ago	MIT	A	121	Claude Code
lesson-gateyarlson/yarstack	Agent	3	2d ago	MIT	A	38	Claude Code
builderStephenQiu30/stephen-claude	Agent	2	3mo ago	MIT	A	22	Claude Code

nothing-new-under-the-sun