Borrowing it
Nothing to install: this file belongs to tobitege/Flowery.Uno. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tobitege/Flowery.Uno/main/AGENTS.mdgit clone --depth 1 https://github.com/tobitege/Flowery.UnoWrote 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/instructions/tobitege/flowery.uno/agents-md)<a href="https://agentmods.dev/instructions/tobitege/flowery.uno/agents-md"><img src="https://agentmods.dev/badge/instructions/tobitege/flowery.uno/agents-md/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/instructions/tobitege/flowery.uno/agents-md"><img src="https://agentmods.dev/badge/instructions/tobitege/flowery.uno/agents-md.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 | $0.04608 | $0.04608 |
| Opus 5.5 | $0.01843 | $0.01843 |
| Sonnet 5.5 | $0.00922 | $0.00922 |
| Haiku 4.5 | $0.00461 | $0.00461 |
Grade A, and why
Flowery.Uno AGENTS.md 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Rules
Agent Behavior
CRITICAL: THE 5-ITERATION RULE (Communication Before Scope Changes)
THIS IS NON-NEGOTIABLE. VIOLATION OF THIS RULE IS UNACCEPTABLE.
The Problem This Solves: The AI often starts a targeted fix, then mid-execution decides "this is too complex, let me simplify/rewrite this" — and proceeds to rewrite several hundred lines of code the user never asked to touch. This creates massive diffs, introduces regressions, and destroys context.
The Rule: During multi-tool inference (not chat with user), if an approach isn't working after 5 consecutive attempts, the AI MUST:
- STOP making unsupervised changes
- Report what was attempted and why it's not working
- ASK the user before trying a different approach or expanding scope
- NEVER silently change direction - approach/scope changes require user awareness
Clarification (Scope of This Rule): This rule is about unsupervised approach changes during the AI's own multi-tool execution. It does NOT limit interactive back-and-forth with the user. If the user is engaged and responding, keep working, but still explicitly communicate any approach/scope change before doing it.
Specifically FORBIDDEN behaviors:
- Silently deciding "this code is messy, let me refactor it while I'm here"
- Expanding from a 10-line fix to a 200-line rewrite without informing the user first
- Switching fundamental approaches (e.g., Grid → Canvas, inheritance → composition) mid-execution without asking
- "Simplifying" code by rewriting large sections the user didn't request
What this rule does NOT prevent:
- Continuing to help when the user is actively engaged in conversation
- Discussing options and alternatives with the user
- Making changes the user explicitly requests or approves
- Asking clarifying questions
- Fixing root causes in other files — but TELL the user first (e.g., "The bug in
DaisyButtonis caused by logic inDaisyControlExtensions. I'll need to fix it there. Proceed?")
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.
- 13d ago First seen · 358 lines · 4,608 tokens per session scan A d1a24b0b19b4
Flowery.Uno AGENTS.md is an instructions file published in the GitHub repository tobitege/Flowery.Uno (16 stars, last pushed today), licensed MIT. It adds 4,608 tokens to every session, about $0.0184 per session on Opus 5.5. 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 2026-10-02.
Other instructions, from other repositories
plan-forge api-patterns.instructions.md
API patterns for .NET — REST conventions, ProblemDetails, pagination, versioning, error responses.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.