archcore-context

A set of rules for working with Archcore, a Git-based project knowledge base stored in .archcore documents. It describes the available tools and document conventions.

In plain words
What is it for?
Use it when listing, reading, creating, updating, removing, or linking Archcore documents through its MCP tools.
Why use it?
It prevents direct file edits that could bypass validation, templates, or the record of synchronized documents and relationships.

Cursor rule

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 rules/archcore-ai/plugin/archcore-context
Clone the repo
git clone --depth 1 https://github.com/archcore-ai/plugin
Per session 234 This file is loaded in full into every session.
When invoked 234 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 $0.00234 $0.00234
Opus 5 $0.00117 $0.00117
Sonnet 5 $0.00047 $0.00047
Haiku 4.5 $0.00023 $0.00023

Measured yesterday against content hash 5d2b5eab40e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

archcore-context 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.

plugins/archcore/rules/archcore-context.mdc · 24 lines

What it actually says

Archcore — Git-native context for AI coding agents

You have Archcore MCP tools available for managing the .archcore/ knowledge base.

MCP Tools

  • list_documents — query documents by type, status, category, tags
  • get_document — read full content + metadata + relations
  • create_document — create new document with validation and templating
  • update_document — modify existing document
  • remove_document — delete document and clean up relations
  • add_relation — link two documents (related, implements, extends, depends_on)
  • remove_relation — unlink documents
  • list_relations — query the relation graph

Critical Rule

All .archcore/ document operations MUST go through MCP tools. Never write directly to .archcore/*.md files — use create_document, update_document, or remove_document instead. This ensures validation, templates, and the sync manifest stay consistent.

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 · 24 lines · 234 tokens per session scan A 5d2b5eab40e4

Subscribe to this mod's changes

archcore-context is a cursor rule published in the GitHub repository archcore-ai/plugin (53 stars, last pushed 15d ago), licensed Apache-2.0. It adds 234 tokens to every session, about $0.0012 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.