What is cadastre AGENTS.md?

A project instruction guide for Cadastre, a catalogue of infrastructure facts and policies exposed through an API, MCP server, and graphical interface.

Use it when working on Cadastre code, setting up a client, contributing to the project, or retrieving infrastructure context.

It tells coding agents how to use the right interface, handle connection details, and avoid unsafe actions such as changing DNS or exposing secrets.

cadastre AGENTS.md — Instructions file for Codex and OpenCode by TheDancingDeveloper-org: A project instruction guide for Cadastre, a catalo

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/thedancingdeveloper-org/cadastre/agents-md

Clone the repo

git clone --depth 1 https://github.com/TheDancingDeveloper-org/cadastre

Made for: Codex, OpenCode.

Per session 1,053 This file is loaded in full into every session.

When invoked 1,053 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.

Model	Per session	Once invoked
Fable 5	$0.01053	$0.01053
Opus 5	$0.00526	$0.00526
Sonnet 5	$0.00211	$0.00211
Haiku 4.5	$0.00105	$0.00105

Measured 2d ago against content hash 23d97ca34d5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cadastre 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 · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cadastre agent and contributor guide

Cadastre records infrastructure facts and policy. It does not deploy workloads, mutate DNS/VPN/orchestrators, execute commands on hosts, or return secret values. The HTTP API, MCP server, and GUI are application interfaces over the same SQLite-backed catalog.

Using Cadastre

Use the networked MCP endpoint when one is supplied by the deployment. For clients that need stdio, install the published package extra and run the remote-only bridge. The ordinary HTTP API is useful for scripts and GUI integrations; /mcp is the MCP transport and must not be substituted with /brief.

MCP:  ${CADASTRE_MCP_URL}   (Streamable HTTP, normally ends in /mcp)
API:  ${CADASTRE_HTTP_URL}  (ordinary HTTP/API base, normally serves /brief)

The endpoint, TLS identity, and authentication method are deployment inputs. Never guess a hostname, port, network, or secret path. Tokens belong in a protected environment variable or file and never in URLs, argv, client JSON, catalog data, logs, or agent-facing output.

At the start of a session:

MCP:  call brief, then context_for(intent)
API:  GET  $CADASTRE_HTTP_URL/brief
      POST $CADASTRE_HTTP_URL/context-for  {"intent":"..."}

Before committing a deployment artifact, run check through MCP or the API:

MCP:  check(artifact, kind)
API:  POST $CADASTRE_HTTP_URL/check

Read provenance and trust state on every answer. stale, unverified, and contested data must be reported before it influences a decision. Read the exclusions returned by context_for; do not route around a rejected candidate.

If the catalog is wrong, use the gated write operation (add, update, delete, or annotate) through the supported client/API. A catalog write changes the map only; it never changes the estate. Source-authoritative entities and observed evidence may be refused by design. A refusal is an answer, not an invitation to bypass the gate.

Client setup

The published package includes cadastre-mcp-remote:

Read the full file on GitHub · 114 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.

2d ago First seen · 114 lines · 1,053 tokens per session scan A 23d97ca34d5f

Subscribe to this mod's changes

cadastre AGENTS.md is an instructions file published in the GitHub repository TheDancingDeveloper-org/cadastre (0 stars, last pushed 7d ago), licensed MIT. It adds 1,053 tokens to every session, about $0.0053 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.

ai-agents homelab infrastructure infrastructure-as-code inventory

cadastre AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Cadastre agent and contributor guide

Using Cadastre

Client setup

What this file has done since we first saw it

Other instructions, from other repositories

infra-lens-mcp AGENTS.md

Cotal AGENTS.md

selfhost-ai CLAUDE.md

cli CLAUDE.md

agent-skills AGENTS.md

homelab-monitor CLAUDE.md