daedal-map CLAUDE.md

daedal-map CLAUDE.md is an instructions file for coding agents from xyver/daedal-map. It costs 1,004 tokens per session, scanned A, original, MIT.

Repository instructions for a public county-map application, including where to find architecture guidance and how the application encodes data.

In plain words
What is it for?
They are for development in this repository, especially API responses, request decoding, frontend data fetching, and project orientation.
Why use it?
They prevent contributors from exposing private material or using the wrong JSON-based data handling when the project requires MessagePack, a compact binary format.

Instructions file

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/xyver/daedal-map/claude-md
Clone the repo
git clone --depth 1 https://github.com/xyver/daedal-map

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 daedal-map CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xyver/daedal-map/claude-md.svg)](https://agentmods.dev/instructions/xyver/daedal-map/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/xyver/daedal-map/claude-md"><img src="https://agentmods.dev/badge/instructions/xyver/daedal-map/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,004 This file is loaded in full into every session.
When invoked 1,004 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 5.1 $0.01004 $0.01004
Opus 5 $0.00502 $0.00502
Sonnet 5 $0.00201 $0.00201
Haiku 4.5 $0.00100 $0.00100

Measured yesterday against content hash ff27d2276526, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

daedal-map 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 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.

CLAUDE.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

County Map - Public Repo Instructions

Rules for working inside county-map/, the public application repo. This file holds durable rules only, not a map of the codebase.

For architecture, request lifecycle, and which doc owns what, read docs/CONTEXT.md first. That is the start-here router and it stays current. Do not use this file for orientation.


This repo is public

Everything here is world-readable. Data processing scripts, internal planning, business docs, and operational runbooks belong in the private repo, not here.


When asked to read, research, search, or investigate something, do it completely before answering or building. Partial reads that agree with each other feel like coverage and are not.

Docs before code. Start at docs/CONTEXT.md, the start-here router. Follow every route it names for the topic, not just the first one that matches the immediate question - the owning doc usually names the owning code and the known gaps.

Read to the end. Do not stop when the immediate question is answered. Ownership tables, change procedures, and "remaining gaps" sections sit at the bottom of a doc, and those are the parts that say whether the thing you are about to build already exists.

Finish the search before concluding. Do not cap a discovery search with head and treat the result as the inventory - results sort alphabetically, so a cap silently hides whatever sorts late. Either take the full list, or count it first and say out loud that you are looking at a sample.

Search by concept, not by guessed implementation. The thing that already exists may be a .md, .json, or .csv rather than the .py you assumed. Search all file types before concluding nothing owns a job.

Assume an owner exists. Before writing a new script, table, or mapping, find the current owner and extend it. A parallel path that duplicates an existing one is worse than no change.


Read the full file on GitHub · 122 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 Changed · +31 lines · +322 tokens per session ff27d2276526
  2. 5d ago First seen · 91 lines · 682 tokens per session scan A 32b5a74e53d7

Subscribe to this mod's changes

daedal-map CLAUDE.md is an instructions file published in the GitHub repository xyver/daedal-map (2 stars, last pushed today), licensed MIT. It adds 1,004 tokens to every session, about $0.0050 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.