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/javaderek/brink/claude-mdgit clone --depth 1 https://github.com/JavaDerek/brinkWrote 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/javaderek/brink/claude-md)<a href="https://agentmods.dev/instructions/javaderek/brink/claude-md"><img src="https://agentmods.dev/badge/instructions/javaderek/brink/claude-md.svg" alt="Measured on agentmods" 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 | $0.03455 | $0.03455 |
| Opus 5 | $0.01728 | $0.01728 |
| Sonnet 5 | $0.00691 | $0.00691 |
| Haiku 4.5 | $0.00346 | $0.00346 |
Grade A, and why
brink CLAUDE.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 3d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brink — Claude Context
What This Is
A single-player, cinematic geopolitical roleplay: you are the supreme executive of a great power, taking calls from world leaders and making decisions, in a persistent world grounded in current real-world geopolitics.
Built on a fork of DMCP (an MCP server for LLM-run RPGs),
with a rules core ported from the BalanceOfTerror Python engine (source of truth at
~/BalanceOfTerror; the port target is TypeScript — no Python runs here).
REBOOT-DESIGN-AND-REQUIREMENTS.md is the authority. Read it before making design decisions. Section numbers below refer to it.
The division of labor (§2.1)
- The LLM is the Game-Master. It classifies a fuzzy action into which mechanic fires, narrates, and calls tools. It never adjudicates.
- The MCP server is referee + ledger. Authoritative resolution, persistence, and the handful of rules the GM cannot talk its way out of.
Hard rules — violations are bugs, not style opinions
- Show, don't tell (Pillar 0, §1). The player-facing surface must never state a disposition or a
raw value. No
DOCTRINE: HAWK, nocohesion 80.0, nohostility: TENSE, no(DOVE advisor). The player deduces state from behavior, dialogue, and consequence — you learn your intel chief is a dove because she's wrong about Korea three times, not from a label. - Resolve, then narrate (§2.1a). The GM never narrates an outcome before the server returns it. It calls the resolve tool, receives an authoritative outcome payload carrying an explicit narration constraint, and narrates from that payload. As florid as it likes about the how; it can never lie about the what.
- No credential in the working tree (§2.4). The GM runs keyless on a Claude subscription. There is
no pay-per-token API key in this repo, ever. Development runs against a mock GM backend; the human
installs real auth at the end, outside any agent's reach.
Specifically: the launcher must assert
ANTHROPIC_API_KEY,ANTHROPIC_AUTH_TOKEN, and the cloud-provider vars are absent, and fail loudly if present — in non-interactive mode (claude -p) a present key silently wins with no prompt. Never pass--bare. - Only three enforced rules (§4.2). These are the only things the GM cannot override. Resist a
fourth:
- Prestige is zero-sum and conserved across the powers.
- DEFCON is bounded [1–5]; DEFCON 1 is shared-loss nuclear war, no winner.
- A crisis countdown ticks and lands regardless of the fiction — real state change, not narration.
- Never pattern-match meaning. No game state is ever derived by matching words, phrases or regexes against natural language — not the player's input, not the GM's narration, not prose this server generated itself. If you have Haiku in your right hand, do not reach for a word list with your left.
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.
- 3d ago First seen · 217 lines · 3,455 tokens per session scan A 84549c98e154
brink CLAUDE.md is an instructions file published in the GitHub repository JavaDerek/brink (0 stars, last pushed 1mo ago), licensed MIT. It adds 3,455 tokens to every session, about $0.0173 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.