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.
npx agentmods add instructions/dravensoft-dev/arena/agents-mdgit clone --depth 1 https://github.com/dravensoft-dev/arenaWhat 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 | $0.05646 | $0.05646 |
| Opus 5 | $0.02823 | $0.02823 |
| Sonnet 5 | $0.01129 | $0.01129 |
| Haiku 4.5 | $0.00565 | $0.00565 |
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 2d 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 — 295 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 this table used to have no row for.
| 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 |
| 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.
- 2d 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 9d ago), licensed MIT. It adds 5,646 tokens to every session, about $0.0282 per session on Opus 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
spartan CLAUDE.md
Instructions for spartan-ng/spartan, covering working in this repo (notes for claude / ai agents), before pushing: run the ci checks locally and pull requests.
kolibri copilot-instructions.md
Copilot instructions for public-ui/kolibri, covering github copilot instructions for kolibri repository, kolibri overview, essential setup commands, 1. install node.js 22 and 2. enable pnpm.
kolibri AGENTS.md
AGENTS.md instructions for public-ui/kolibri, covering agent instructions, handling hints, 🚨 format-first rule, semantic versioning and project structure.
ng-blatui AGENTS.md
Instructions for anousss007/ng-blatui, covering ng-blatui — agent guide, use the official angular tooling, hard rules (this repo), commands and after changing a component's public api.
core-web copilot-instructions.md
Copilot instructions for db-ux-design-system/core-web: All development instructions, build commands, validation steps, coding rules, and the pull request workflow are maintained in AGENTS.md at the repository root. Read that file first before starting any task.
core-web AGENTS.md
AGENTS.md instructions for db-ux-design-system/core-web, covering db ux design system v3 core web, working effectively, required prerequisites, bootstrap and setup and build and test.