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.
curl -O https://raw.githubusercontent.com/HorizunGroup/horizun-pbi-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/HorizunGroup/horizun-pbi-mcpWrote 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.
[](https://agentmods.dev/instructions/horizungroup/horizun-pbi-mcp/agents-md)<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.
<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>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 5.1 | $0.03288 | $0.03288 |
| Opus 5 | $0.01644 | $0.01644 |
| Sonnet 5 | $0.00658 | $0.00658 |
| Haiku 4.5 | $0.00329 | $0.00329 |
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.
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
- stdout is the JSON-RPC channel. All logging goes to stderr or a file. A debug
print()breaks the client connection. - Never overwrite JSON that doesn't parse. If it can't be read, abort.
- Every write to the user's project: backup before, re-read after.
- No write path leaves the active project. Use
ensure_within_base(). - No fields are invented that don't exist in the model. If a field doesn't exist, report it; don't guess.
- Destructive tools require
confirm=true. - Prefer cloning a real template over hand-building visual JSON.
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.
- 6d ago Changed · +16 lines · +184 tokens per session dbf48506a30a
- 12d ago First seen · 243 lines · 3,104 tokens per session scan A 763319e2abce
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.
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.
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.
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).
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.
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.
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).