cli AGENTS.md

A set of repository instructions for the Archcore CLI, MCP server, host integrations and document templates. It defines how technical documentation should identify subjects, constraints and required actions.

In plain words
What is it for?
It is for work on repository instructions, README files, documentation, templates and Markdown embedded in source code.
Why use it?
It helps people and coding agents understand project rules without guessing, while directing them to the central documentation policy.

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/archcore-ai/cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/archcore-ai/cli

Made for: Codex, OpenCode.

Per session 2,684 This file is loaded in full into every session.
When invoked 2,684 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 $0.02684 $0.02684
Opus 5 $0.01342 $0.01342
Sonnet 5 $0.00537 $0.00537
Haiku 4.5 $0.00268 $0.00268

Measured 2d ago against content hash e563a15642fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cli 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 · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Agent Instructions

Purpose

This repository develops the Archcore CLI, MCP server, host integrations, and document templates.

Write technical documentation so that human readers and AI agents can identify the subject, understand the constraints, and apply the information without guessing.

Two profiles govern every document: an ASD-STE100-inspired profile constrains the sentence, and an ISO 24495-1-inspired profile constrains the structure. Both apply everywhere; the document type decides which half binds and which half advises.

The assignment — profile, line format, and metric per document type — lives in the shared Archcore rule concepts/document-prose-canon, mounted read-only from the archcore global source. Do not restate that assignment here, and do not classify a document into a profile by hand when the rule already assigns one to its type.

This policy is an internal writing profile. It is not a claim of compliance, certification, or approval by ASD, ISO, or any standards organization.

Scope

Apply this policy when creating or updating:

  • .archcore/**/*.md;
  • README.md;
  • docs/**/*.md;
  • templates/**/*.md;
  • Markdown embedded in Go source;
  • CLI help text and error messages;
  • MCP tool descriptions and prompts;
  • agent instruction files;
  • user-facing installation, migration, recovery, and troubleshooting instructions.

Do not rewrite or translate:

  • Go identifiers;
  • package names;
  • commands;
  • flags;
  • paths;
  • configuration keys;
  • MCP tool names;
  • JSON fields;
  • document type names;
  • literal values;
  • generated output;
  • exact quotations from external sources.

Precedence

Apply instructions in this order:

  1. Explicit user requirements.
  2. Accepted rules and decisions in .archcore/.
  3. Type-specific document contracts and templates.
  4. This repository writing policy.
  5. General stylistic preferences.

When instructions conflict, follow the higher-priority instruction.

Archcore-first context

Before researching project behavior, architecture, conventions, or implementation approaches:

Read the full file on GitHub · 306 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 · 306 lines · 2,684 tokens per session scan A e563a15642fa

Subscribe to this mod's changes

cli AGENTS.md is an instructions file published in the GitHub repository archcore-ai/cli (61 stars, last pushed 15d ago), licensed Apache-2.0. It adds 2,684 tokens to every session, about $0.0134 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.