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.
git clone --depth 1 https://github.com/fahrellgiovanny/nothing-new-under-the-sunWrote 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.
[](https://agentmods.dev/agents/fahrellgiovanny/nothing-new-under-the-sun/nothing-new-under-the-sun)<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.
<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>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 | $0.00067 | $0.02129 |
| Sonnet 5 | $0.00027 | $0.00851 |
| Haiku 4.5 | $0.00013 | $0.00426 |
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 12d 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 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?
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.
- 12d ago First seen · 457 lines · 134 tokens per session scan C 8d38e4653543
nothing-new-under-the-sun is an agent published in the GitHub repository fahrellgiovanny/nothing-new-under-the-sun (8 stars, last pushed 1mo ago), licensed MIT. It adds 134 tokens to every session and 4,257 once invoked, about $0.0007 per session on Opus 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.
Other agents, from other repositories
docs-app-builder
Use this agent to build a documentation application as a React app — from a repo's README, docs folder, or code. Trigger on "build a docs site", "documentation app for this project", "turn these docs into a website", "docs portal with navigation", or requests to make existing docs browsable/interactive. Returns a…
database-architect
Use this agent for database design and change work: schema design, indexing strategy, query optimization, migration safety, and engine selection. Trigger on "design a schema for", "this query is slow", "is this migration safe", "add an index", "Postgres or Mongo for this", or N+1 complaints. Returns schema/DDL with…
event-driven-designer
Use this agent to design or review asynchronous, event-driven systems: queues, streams, pub/sub, sagas, outbox patterns, DLQs. Trigger on "design an event pipeline", "Kafka or SQS", "review our consumer", "we're losing/duplicating messages", "how do I make this async", or distributed-transaction questions. Returns a…
system-architecture-reviewer
Use this agent for codebase architecture mapping, coupling analysis, bounded-context discovery, monolith-split planning, and deployment-safety review. Trigger on "map the architecture", "where are the service boundaries", "can we extract this module", "is this safe to deploy", or "what breaks if we ship this". Returns…
builder
An agent role for making the smallest needed code or documentation change. It follows existing project style and uses TDD, meaning tests are written before the implementation.
explorer
A research agent that gathers facts about a codebase before implementation, including relevant files, dependencies, entry points, and existing conventions.