agentmods.dev

groundlane AGENTS.md

A project instruction file for Groundlane, an open-source TypeScript project. It defines the project’s boundaries, architecture, web-access rules, and provider and quota policies.

In plain words
What is it for?
Use it when changing Groundlane’s worker, container, core, adapter, tool, test, or documentation code.
Why use it?
It gives coding agents shared rules for where code belongs and how the project should access external services.

Instructions file for CodexOpenCode

0 2d ago A scan 1,251 tokens original Apache-2.0
View the source file lanefoundry/groundlane
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/lanefoundry/groundlane/agents-md
Clone the repo
git clone --depth 1 https://github.com/lanefoundry/groundlane

Made for: Codex, OpenCode.

Per session 1,251 This file is loaded in full into every session.
When invoked 1,251 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 $0.01251 $0.01251
Opus 5 $0.00626 $0.00626
Sonnet 5 $0.00250 $0.00250
Haiku 4.5 $0.00125 $0.00125

Measured 2d ago against content hash e5bf36817321, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

groundlane 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.

AGENTS.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Groundlane agent instructions

Project boundary

Groundlane is an independent open-source TypeScript project. It is not part of DaoDao and must not import DaoDao-specific code, configuration, terminology, or deployment assumptions.

Architecture

  • src/worker/: Cloudflare Worker entry, authentication, routing, and Container lifecycle.
  • src/container/: Node.js remote MCP HTTP server running in a Cloudflare Container.
  • src/core/: pure orchestration, policies, limits, budgets, and contracts.
  • src/adapters/: HTTP, reader, browser, search, and provider integrations.
  • src/tools/: MCP tool definitions and handlers.
  • test/: unit, contract, integration, and regression tests.
  • docs/: product decisions, configuration, deployment, and time-sensitive research.

Keep provider-specific request and response mapping in src/adapters/. Keep routing, quota policy, validation, and shared contracts provider-neutral in src/core/.

Dogfood Groundlane for web access

  • Use Groundlane's web_fetch, web_search, and web_extract for public-web research, documentation checks, and representative smoke tests.
  • This rule applies to the primary agent and every subagent.
  • When changing Groundlane itself, prefer running the current checkout locally with a temporary development auth token so research exercises the code being edited. Use the deployed MCP only when the task explicitly concerns the deployed version.
  • web_fetch and web_extract do not require a third-party search key. web_search must fail closed when no configured search provider is available.
  • If Groundlane cannot retrieve a required source, record the exact bounded failure and treat it as product evidence. Do not claim that an untested provider path works.
  • Browser rendering proves JavaScript execution, not reliable CAPTCHA or managed-challenge bypass. State the observed boundary accurately.

Provider and quota rules

  • Treat provider pricing, quota, API contracts, reset cadence, and product availability as time-sensitive. Verify them with Groundlane against official provider sources before implementation.
  • Keep requests, successful requests, credits, currency balances, browser time, concurrency, RPM, daily pools, monthly pools, balance top-ups, and one-time trials as distinct concepts. Never convert between them without a verified rate.
  • Local attempt budgets are safety guardrails, not provider billing truth. Document whether counters reset on process restart and whether instances share state.
  • A provider is implemented only when it has a real runtime path, configuration, secret forwarding where applicable, bounded error handling, and contract tests. Catalog or UI presence alone is not execution proof.
  • Keep one-time and eligibility-gated allowances opt-in unless automatic routing has an explicit, conservative hard stop.
  • Never enable provider PAYG or automatic top-up implicitly.

Read the full file on GitHub · 123 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. 2d ago First seen · 123 lines · 1,251 tokens per session scan A e5bf36817321

Subscribe to this mod's changes

groundlane AGENTS.md is an instructions file published in the GitHub repository lanefoundry/groundlane (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,251 tokens to every session, about $0.0063 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens