openmapstack AGENTS.md

openmapstack AGENTS.md is an instructions file for Codex, OpenCode from jaakla/openmapstack. It costs 1,820 tokens per session, scanned A, original, MIT.

A repository guide named AGENTS.md for contributors and coding agents working on OpenMapStack, a codebase for a geospatial agent skill.

In plain words
What is it for?
It is for understanding the repository structure, maintainer rules, development workflow, and testing responsibilities.
Why use it?
It explains which files are authoritative and how to start work without confusing the skill's user workflow with the repository's maintenance work.

Instructions file for CodexOpenCode

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/jaakla/openmapstack/agents-md
Clone the repo
git clone --depth 1 https://github.com/jaakla/openmapstack

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 openmapstack AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jaakla/openmapstack/agents-md.svg)](https://agentmods.dev/instructions/jaakla/openmapstack/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jaakla/openmapstack/agents-md"><img src="https://agentmods.dev/badge/instructions/jaakla/openmapstack/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,820 This file is loaded in full into every session.
When invoked 1,820 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 $0.01820 $0.01820
Opus 5 $0.00910 $0.00910
Sonnet 5 $0.00364 $0.00364
Haiku 4.5 $0.00182 $0.00182

Measured yesterday against content hash 65da789b13a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openmapstack 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 yesterday.

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 · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the canonical maintainer guide for coders (including AI coding agents) working on the OpenMapStack repository. Keep repository-wide development guidance here and keep it vendor-neutral.

What this repository is

OpenMapStack is a managed agent-skill codebase, not an OpenMapStack GIS analysis project.

The repository develops and quality-assures a distributable geospatial agent skill:

  • SKILL.md and references/ are product artifacts consumed by agents in other projects.
  • templates/ and examples/ define and demonstrate the artifacts the skill should cause those agents to produce.
  • openmapstack/ is executable support code for validating, running, inspecting, and verifying those artifacts.
  • evals/ measures whether the skill and its supporting contract produce correct, reproducible behavior.
  • tests/ tests the repository's Python implementation and eval infrastructure.

Do not treat SKILL.md as maintainer instructions for this repository. Read or edit it when the task concerns the shipped skill behavior, but do not preload or follow its GIS workflow merely because you are modifying this codebase.

Sources of truth

Read only what is relevant to the current issue.

Area Source of truth
Shipped agent behavior SKILL.md
Detailed shipped guidance references/*.md
Reproducible project contract references/project-spec.md
Project templates templates/
Canonical worked integration example examples/tartu-development/
CLI, schema handling, reusable checks openmapstack/
Eval architecture, cases, scoring, live adapters evals/README.md, evals/
Maintainer architecture/rationale/debugging knowledge docs/maintainers/
Implementation tests tests/
User-facing install and usage docs README.md

Prefer the code/schema/test that owns a behavior over a prose summary elsewhere. Avoid duplicating detailed rules between files; link to the authoritative source instead.

Read the full file on GitHub · 147 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. yesterday First seen · 147 lines · 1,820 tokens per session scan A 65da789b13a4

Subscribe to this mod's changes

openmapstack AGENTS.md is an instructions file published in the GitHub repository jaakla/openmapstack (68 stars, last pushed yesterday), licensed MIT. It adds 1,820 tokens to every session, about $0.0091 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 2026-09-03.