Borrowing it
Nothing to install: this file belongs to sparko161-droid/pyrus_mcp_bd_complect. 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/sparko161-droid/pyrus_mcp_bd_complect/main/AGENTS.mdgit clone --depth 1 https://github.com/sparko161-droid/pyrus_mcp_bd_complectWrote 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/sparko161-droid/pyrus_mcp_bd_complect/agents-md)<a href="https://agentmods.dev/instructions/sparko161-droid/pyrus_mcp_bd_complect/agents-md"><img src="https://agentmods.dev/badge/instructions/sparko161-droid/pyrus_mcp_bd_complect/agents-md.svg" alt="Measured on agentmods" 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 | $0.00776 | $0.00776 |
| Opus 5 | $0.00388 | $0.00388 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
pyrus_mcp_bd_complect 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Pyrus MCP Server Constitution v2
Mission
Build the pyrus_mcp Python server as a production-grade external MCP integration for multiple authorized employees/AI hosts, replacing the closed-source Railway service.
The same repository also defines the future Knowledge MCP architecture. Knowledge MCP is a separate service and datastore; it is not a module inside Pyrus MCP.
Authority
Human Architect is the final authority for product, architecture, security and production release. AI CTO orchestrates agents and resolves cross-team dependencies. Chief Architect owns technical architecture.
Normative sources
Read these before implementation:
IMPLEMENTATION_PLAN.mddocs/architecture/system-architecture-v2.mddocs/architecture/contracts-v2.mddocs/planning/production-roadmap-v2.mdtasks/registry.yamldocs/qa/gates.mddocs/ai-team/agent-registry.yaml
For parity work, use contracts/pyrus-tool-catalog.yaml. It is currently a recovery scaffold and is not authoritative until Phase 0 contract recovery is approved.
Do not reference absent or unversioned contract files as if they were sources of truth.
Before coding
- Read the applicable phase and task from
tasks/registry.yaml. - Read the relevant architecture and contract document.
- Check all declared dependencies.
- Search the repository for an existing implementation before introducing a new abstraction.
- If a requirement or contract is missing, create a discovery task and block the affected implementation instead of guessing.
Phase discipline
Follow IMPLEMENTATION_PLAN.md and tasks/registry.yaml.
Do not implement a compatibility tool before its Pyrus API contract, MCP contract, security contract and fixture evidence exist.
Do not implement public multi-user access using a single global SERVER_AUTH_TOKEN.
Do not use SQLite as the durable production store.
Architecture rules
Required production path:
MCP tool -> Service -> PyrusClient -> Pyrus API
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 First seen · 106 lines · 776 tokens per session scan A ea7333573b81
pyrus_mcp_bd_complect AGENTS.md is an instructions file published in the GitHub repository sparko161-droid/pyrus_mcp_bd_complect (0 stars, last pushed 17d ago), licensed Apache-2.0. It adds 776 tokens to every session, about $0.0039 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.
Other instructions, from other repositories
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).
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.
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).
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.