horizun-pbi-mcp: Instructions file for Codex

AGENTS.md

horizun-pbi-mcp AGENTS.md is an instructions file for Codex, OpenCode from HorizunGroup/horizun-pbi-mcp. It costs 3,288 tokens per session, scanned A, original, Apache-2.0.

A repository rulebook for Horizun PBI MCP, an MCP server that provides tools for working with Power BI. MCP is a standard way for AI clients to use external tools.

In plain words
What is it for?
Use it when changing MCP tools, classifying their risks, running required checks, or reviewing files and test data before a contribution.
Why use it?
It helps prevent changes that break the server's existing tool interface, while keeping real data and destructive actions controlled.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is HorizunGroup/horizun-pbi-mcp's own configuration. It tells Codex and OpenCode how to work on horizun-pbi-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything horizun-pbi-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to HorizunGroup/horizun-pbi-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/HorizunGroup/horizun-pbi-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/HorizunGroup/horizun-pbi-mcp

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 horizun-pbi-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/horizungroup/horizun-pbi-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/horizungroup/horizun-pbi-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/horizungroup/horizun-pbi-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/horizungroup/horizun-pbi-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for horizun-pbi-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/horizungroup/horizun-pbi-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/horizungroup/horizun-pbi-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,288 This file is loaded in full into every session.
When invoked 3,288 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.03288 $0.03288
Opus 5 $0.01644 $0.01644
Sonnet 5 $0.00658 $0.00658
Haiku 4.5 $0.00329 $0.00329

Measured 6d ago against content hash dbf48506a30a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

horizun-pbi-mcp 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 6d 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 · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository rules for agents

Operating instructions for any agent (or person) modifying Horizun PBI MCP. They take priority over any general convention.


1. Before touching anything

python -m pytest -q                    # must pass green
python scripts/doctor.py               # must exit with code 0

If the baseline is already broken, fix it or report it first. Don't build on red.


2. The MCP contract is untouchable

The 34 baseline tools are frozen in tests/golden/tools_v1.json.

Forbidden without explicit approval:

  • removing a tool
  • renaming a tool
  • removing a parameter
  • adding a required parameter
  • changing a parameter's type
  • changing a default value
  • changing the response shape

Allowed:

  • adding new tools
  • adding optional parameters with a default
  • adding new fields to the response dict
  • improving descriptions

Adding a tool also means classifying it in src/tools/risk.py. The suite fails if you don't: an unclassified tool is announced to the client as destructive — which is the safe default, but the table has to say so out loud. Never declare as read_only anything that calls guard_mutation or writes a file; tests/test_tool_annotations.py checks that against the code, not against the docs.

Check at any time:

python -m tests.contract_utils

Returns 0 if there are no breaks, 1 if there are, with a report stating what changed and whether it breaks compatibility — not a dump of two JSONs.

After a deliberate, approved change:

python -m tests.contract_utils --write

3. Invariants no phase can break

  1. stdout is the JSON-RPC channel. All logging goes to stderr or a file. A debug print() breaks the client connection.
  2. Never overwrite JSON that doesn't parse. If it can't be read, abort.
  3. Every write to the user's project: backup before, re-read after.
  4. No write path leaves the active project. Use ensure_within_base().
  5. No fields are invented that don't exist in the model. If a field doesn't exist, report it; don't guess.
  6. Destructive tools require confirm=true.
  7. Prefer cloning a real template over hand-building visual JSON.

Read the full file on GitHub · 259 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. 6d ago Changed · +16 lines · +184 tokens per session dbf48506a30a
  2. 12d ago First seen · 243 lines · 3,104 tokens per session scan A 763319e2abce

Subscribe to this mod's changes

horizun-pbi-mcp AGENTS.md is an instructions file published in the GitHub repository HorizunGroup/horizun-pbi-mcp (13 stars, last pushed 6d ago), licensed Apache-2.0. It adds 3,288 tokens to every session, about $0.0164 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens