agentmods.dev

Surface AGENTS.md

Surface AGENTS.md is an instructions file for Codex, OpenCode from Aaryan-Kapoor/Surface. It costs 1,440 tokens per session, scanned A, original, MIT.

Repository instructions for Surface, a local display system where AI agents send content through one shared command-line tool. They describe its server, browser app, data storage, service setup, migrations, and agent rules.

In plain words
What is it for?
Use them when developing, testing, building, installing, or troubleshooting the Surface server, client, command-line tool, stored data, or background service.
Why use it?
They give coding agents the project context and commands needed to make changes that fit the existing architecture.

Instructions file for CodexOpenCode

not rated 48 3d ago A scan 1,440 tokens original MIT
View the source file Aaryan-Kapoor/Surface
Install

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.

agentmods
npx agentmods add instructions/aaryan-kapoor/surface/agents-md
Clone the repo
git clone --depth 1 https://github.com/Aaryan-Kapoor/Surface

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for Surface AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aaryan-kapoor/surface/agents-md.svg)](https://agentmods.dev/instructions/aaryan-kapoor/surface/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/aaryan-kapoor/surface/agents-md"><img src="https://agentmods.dev/badge/instructions/aaryan-kapoor/surface/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,440 This file is loaded in full into every session.
When invoked 1,440 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01440 $0.01440
Opus 5 $0.00720 $0.00720
Sonnet 5 $0.00288 $0.00288
Haiku 4.5 $0.00144 $0.00144

Measured 4d ago against content hash 75f795d6427a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Surface 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.

AGENTS.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Surface

Universal display for AI agents. Agents push content via a single shared CLI (surface). Discovery is via SKILL.md at the repo root. Full per-feature docs: docs/README.md.

Stack

  • Server: Express 5 + SQLite (better-sqlite3) + SSE live updates. Routers per concern in server/routes/.
  • Client: Vanilla JS PWA, hash routing, sandboxed iframes via real routes. client/surface.js is the runtime injected into surface HTML.
  • CLI (bin/surface.ts): canonical agent client; bundled to dist/surface.mjs by npm run build (runs on install via prepare; also bundles the server to dist/server.mjs); the npm surface bin points at the bundle. Published as surface-display.
  • Data: ~/.surface/ (db.sqlite + artifacts/ + logs/ + templates/). Override with SURFACE_DATA_DIR.
  • Service: Surface should run once as a per-user supervised service bound to 127.0.0.1 — surface service install picks the native backend (systemd user unit / launchd agent / Windows Scheduled Task), health-gates the start, and logs to ~/.surface/logs/.
  • Migrations: SQLite PRAGMA user_version via server/migrations.ts; fresh-start baseline = v10. Pre-baseline DBs are archived to db.sqlite.bak at boot, never migrated.
  • Templates: built-ins in templates/ (ask, stream, video, board, doc); resolution project .surface/templates → ~/.surface/templates → built-in.
  • MCP (archived in archived/mcp.ts): not installed by default; needs npm i @modelcontextprotocol/sdk to run.

Commands

  • npm run dev — start server on 127.0.0.1:3000
  • npm run service — service entrypoint from source (production supervisors exec dist/server.mjs via surface service install)
  • npm run cli — invoke the CLI from source without npm link
  • npm run test:artifacts — HTTP regression suite (needs a running server; use an isolated SURFACE_DATA_DIR + PORT)
  • npm run test:auth — two-plane trust-model acceptance tests (spawns its own servers)
  • npm run test:startup-access — pairing URL/QR helpers
  • npx tsc --noEmit — TypeScript check

Read the full file on GitHub · 64 lines

Changes

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.

  1. 4d ago First seen · 64 lines · 1,440 tokens per session scan A 75f795d6427a

Subscribe to this mod's changes

Surface AGENTS.md is an instructions file published in the GitHub repository Aaryan-Kapoor/Surface (48 stars, last pushed 3d ago), licensed MIT. It adds 1,440 tokens to every session, about $0.0072 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 2026-08-30.

Planningagent-toolsai-agentsclaude-codeclidashboardhuman-in-the-loop
Related

Other instructions, from other repositories

boardstate AGENTS.md

Instructions for 100yenadmin/boardstate, covering agents & boardstate, 1. give any ai the board (@boardstate/mcp), the tool catalog, conventions for board-building agents and 2. embed a chat agent in your host (@boardstate/agent).

100yenadmin/boardstate · 2,557 tokens

Vibe-Research AGENTS.md

AGENTS.md instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).

simonlin1212/Vibe-Research · 4,469 tokens

mcp-steroid CLAUDE.md

Claude Code instructions for jonnyzzz/mcp-steroid, covering claude.md, agents.md, design philosophy, recursive context lookup (do this before sub-folder work), sub-folder guides and must do.

jonnyzzz/mcp-steroid · 6,916 tokens

ifq-design-skills AGENTS.md

Instructions for peixl/ifq-design-skills, covering agents.md — ifq design skills, first-contact protocol (60 seconds · any runtime), what this repo is, when to engage the skill and zero-install core loop.

peixl/ifq-design-skills · 1,460 tokens

anywidget-mcp AGENTS.md

Instructions for peter-gy/anywidget-mcp, covering anywidget-mcp, commands, architecture, dependency rule and state invariant.

peter-gy/anywidget-mcp · 2,371 tokens

claumon CLAUDE.md

Instructions for fabioconcina/claumon, covering claumon, build & test, architecture and conventions.

fabioconcina/claumon · 678 tokens