Borrowing it
Nothing to install: this file belongs to sumx21t-3310/FloatSoda. 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/sumx21t-3310/FloatSoda/main/AGENTS.mdgit clone --depth 1 https://github.com/sumx21t-3310/FloatSodaWrote 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/sumx21t-3310/floatsoda/agents-md)<a href="https://agentmods.dev/instructions/sumx21t-3310/floatsoda/agents-md"><img src="https://agentmods.dev/badge/instructions/sumx21t-3310/floatsoda/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/sumx21t-3310/floatsoda/agents-md"><img src="https://agentmods.dev/badge/instructions/sumx21t-3310/floatsoda/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 | $0.04600 | $0.04600 |
| Opus 5.5 | $0.01840 | $0.01840 |
| Sonnet 5.5 | $0.00920 | $0.00920 |
| Haiku 4.5 | $0.00460 | $0.00460 |
Grade A, and why
FloatSoda 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 9d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents — Codex, Claude Code (claude.ai/code), and others — when working with code in this repository.
This file is the single source of project instructions for every agent. Codex and other AGENTS.md-aware tools read it directly; Claude Code reads it through a one-line
@AGENTS.mdimport inCLAUDE.md. Put project instructions here, never inCLAUDE.md— anything added there is invisible to every other agent.
Working Style
The repository owner develops hands-on and tracks the implementation themselves. By default, investigate and explain — do not modify code. When asked about a bug or behavior, report the root cause, the relevant files/lines, and (optionally) how a fix would look, but leave the actual implementation to the owner unless they explicitly ask you to make the change.
When you are asked to implement, how much you may take on depends on the kind of work — see the tiers in CONTRIBUTING.md (「コーディングエージェントに任せる範囲」): new APIs that Flutter does not have are implemented by a human; bug fixes start with investigation only; porting Flutter widgets (with Flutter's tests) may be delegated fully.
Output Language
Write all output to the repository owner in Japanese. This is a hard requirement, not a preference.
- Code review — findings, severity reasoning, and suggested fixes are written in Japanese, even though the code and identifiers under review are English.
- Investigation reports — root cause, affected files/lines, and how a fix would look.
- Commit messages and PR titles/bodies.
Do not translate identifiers, type names, file paths, or code fences — those stay verbatim as they appear in the source.
Rationale: FloatSoda treats Japanese as the neutral (default) language — see LOCALIZATION.md. docs/, XML doc comments, and exception messages are all Japanese by design. Review output in Japanese keeps the entire surface consistent for the owner and for the LLMs that relay it to end users. If you feel English "should" be the default here, read LOCALIZATION.md before changing anything.
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 Changed · +20 tokens per session 2913fd692e94
- 10d ago Changed · +2 lines · +131 tokens per session 22ff13390517
- 28d ago Changed · -10 tokens per session 57a47f759e70
- 1mo ago Changed · +1 lines · +185 tokens per session 9d1c00edf251
- 1mo ago Changed · +37 tokens per session 96ab6eed692d
- 2mo ago First seen · 211 lines · 4,237 tokens per session scan A f40b6f394cc7
FloatSoda AGENTS.md is an instructions file published in the GitHub repository sumx21t-3310/FloatSoda (12 stars, last pushed yesterday), licensed MIT. It adds 4,600 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 2026-08-30.
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).