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.
npx agentmods add instructions/altendky/hamster-mcp/agents-mdgit clone --depth 1 https://github.com/altendky/hamster-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/altendky/hamster-mcp/agents-md)<a href="https://agentmods.dev/instructions/altendky/hamster-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/altendky/hamster-mcp/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 | $0.00636 | $0.00636 |
| Opus 5 | $0.00318 | $0.00318 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
hamster-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 5d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Context
For project requirements, architecture, and conventions, see:
Development Workflow
Setup
mise install # Installs Python 3.14, uv, pre-commit, and project tools
uv sync --extra dev # Creates .venv, installs package + dev deps
pre-commit install # Installs git hooks
Running checks
ruff format --check . # Formatting
ruff check . # Linting
mypy # Type checking
pytest src/ # Tests
Rules
- Always use the mise-managed environment. Run
python,ruff,mypy,pytest, etc. from the mise-activated shell or viamise run. Never setPYTHONPATHmanually. - Install via
uv sync, notpip install. The project usesuv.lockfor deterministic dependency resolution. - Do not modify
uv.lockby hand. It is generated byuv lockand updated byuv sync.
Icon generation
Brand icons are generated from brand/source.svg:
mise run generate-icons
The source SVG should contain black stroke-based line art with uniform stroke
width. The script applies amber (#c87f43) fill and halo (3x stroke width),
auto-fits to the canvas, then exports PNG icons at 256x256 and 512x512.
Generated files (written to custom_components/hamster_mcp/brand/):
icon.svg,icon.png,[email protected]
Code Conventions
- Dataclasses everywhere. All classes use
@dataclass. Prefer@dataclass(frozen=True, slots=True)for immutability; use explicitfrozen=Falsewhen mutation is needed. Use.create()classmethods for complex construction. See Principles for details and exception criteria.
Package Structure
src/hamster_mcp/mcp/_core/--- sans-IO protocol core. Must not perform I/O or hold global state. May depend on any library as long as the code itself remains pure.src/hamster_mcp/mcp/_io/--- I/O adapters (async transport). Does not importhomeassistant(HA-independent for testability).src/hamster_mcp/component/--- HA integration. May import anything.custom_components/hamster_mcp/--- HACS deployment shim. Thin re-exports fromhamster_mcp.component.
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.
- 5d ago First seen · 75 lines · 636 tokens per session scan A 31335fdc7f33
hamster-mcp AGENTS.md is an instructions file published in the GitHub repository altendky/hamster-mcp (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 636 tokens to every session, about $0.0032 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
ha-mcp AGENTS.md
AGENTS.md instructions for homeassistant-ai/ha-mcp, covering agents.md, instruction structure, repository structure, worktree workflow and project overview.
ha-dual-smart-thermostat CLAUDE.md
Claude Code instructions for swingerman/ha-dual-smart-thermostat, covering claude.md, project overview, essential commands, development with docker (recommended) and testing - use docker-test for all test runs.
ha-mcp CLAUDE.md
Claude Code instructions for homeassistant-ai/ha-mcp, a project described as: The Unofficial and Awesome Home Assistant MCP Server.
core integrations.instructions.md
Instructions for home-assistant/core, covering file locations, general guidelines, entity platforms, integration quality scale and how rules apply.
Gladys AGENTS.md
AGENTS.md instructions for GladysAssistant/Gladys, covering agents.md, cursor cloud specific instructions, running the app (dev mode), non-obvious caveats and feature specs (spec-first process).
hassio-addons CLAUDE.md
Claude Code instructions for alexbelgium/hassio-addons, covering claude.md, repository overview, add-on directory structure, dockerfile convention and config.yaml schema.