Borrowing it
Nothing to install: this file belongs to dravensoft-dev/arena. 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/dravensoft-dev/arena/main/AGENTS.mdgit clone --depth 1 https://github.com/dravensoft-dev/arenaWrote 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/dravensoft-dev/arena/agents-md)<a href="https://agentmods.dev/instructions/dravensoft-dev/arena/agents-md"><img src="https://agentmods.dev/badge/instructions/dravensoft-dev/arena/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/dravensoft-dev/arena/agents-md"><img src="https://agentmods.dev/badge/instructions/dravensoft-dev/arena/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 | $0.05837 | $0.05837 |
| Opus 5.5 | $0.02335 | $0.02335 |
| Sonnet 5.5 | $0.01167 | $0.01167 |
| Haiku 4.5 | $0.00584 | $0.00584 |
Grade A, and why
arena 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 4d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arena, for whoever changes it
Arena is Dravensoft's design system: a token layer, React and Angular component libraries built
on it, and a shared Tailwind layer. The repository itself is not an npm package, and its root
package.json is dev-only and private; what npm gets is two packages assembled from this tree.
This file routes. Read only what your task needs.
Which job is this?
Building something with Arena (a screen, a prototype, a skin, an integration): read
skills/design/SKILL.md instead. It is the root of that branch and
this file is not, and the two are almost disjoint by design.
Changing Arena itself: stay here. Everything below is reached through this page.
Where each decision goes
Most rows below are indexed by what you are changing. The first two are not, because a reader arriving with a symptom does not know yet what they are changing, and that is the state no other row answers.
| I am here because | Start at |
|---|---|
| something renders or behaves wrong and I do not know which layer owns it | contracts/behaviour/AGENTS.md when it is a role, a key, focus or dismissal, whose last section is why a defect outlives a green run; otherwise the layer, through frameworks/AGENTS.md |
| I do not know whether Arena already has the thing I am about to add | frameworks/INDEX.md, one line per component and which layers ship it. It belongs to the other branch and it is still the only page that answers this, so read that one line and come back; its own pointers are a builder's and not yours |
| a value: a colour, a spacing step, a duration, a delay | contracts/design/AGENTS.md, and TokenTypes.md for the shape it is authored in |
| what a kind of component must DO: roles, keys, focus, dismissal | contracts/behaviour/AGENTS.md |
| what a component PRESENTS: its members | contracts/api/AGENTS.md |
| which of those three a fact belongs to | contracts/AGENTS.md, the roof |
| a component, in one layer or both | frameworks/AGENTS.md, then that layer's own |
| how a component LOOKS | frameworks/tailwind/AGENTS.md |
| a style decision an adopter makes on an instance or a region: a family, a channel, a boundary | contracts/AGENTS.md, its section on who decides how a component looks, then frameworks/tailwind/AGENTS.md |
| what a consumer may build Arena INTO: an import, a peer, a browser global, a server render | frameworks/AGENTS.md, the envelope section, then the layer you are editing. check:architecture fails a withdrawal |
| a playground's seed | frameworks/demos/AGENTS.md |
| a script, a gate, a generator | scripts/AGENTS.md |
| a browsable page or a specimen | intro/AGENTS.md |
| the identity document a project fills in before its first screen | arena-from-scratch/AGENTS.md |
| a style plugin Arena renders, or an entry a project starts from | plugin-style-store/AGENTS.md, and catalogue/ beside it |
| a release, in the order the moves are made | versioning_steps.md, and nothing else until it sends you there |
| the npm channel: what a package is, what CI does with it | frameworks/PACKAGING.md and .github/workflows/AGENTS.md |
| documentation | this page, the two sections below it |
| I am about to write down that something is wrong | DOUBTS.md, which says what counts as a debt and which records beat a paragraph. It is not where a bug report starts; that is the first row |
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.
- 4d ago Changed · +1 lines · +21 tokens per session 020cc3ab9777
- 20d ago Changed · -1 lines · +104 tokens per session f40de16771e1
- 1mo ago Changed · +1 lines · +10 tokens per session 28413e7fcf48
- 1mo ago Changed · +3 lines · +56 tokens per session 9594a9642cbe
- 2mo ago First seen · 295 lines · 5,646 tokens per session scan A 043d1d250a29
arena AGENTS.md is an instructions file published in the GitHub repository dravensoft-dev/arena (2 stars, last pushed 4d ago), licensed MIT. It adds 5,837 tokens to every session, about $0.0233 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 2026-08-31.
Other instructions, from other repositories
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).
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.