What is mcp-stargazing AGENTS.md?

Repository instructions for developers building MCP tools, which are tools that AI agents can call. They define rules for registration, interfaces, responses, testing, and deployment.

Adding tools under the required source directory, registering them correctly, formatting responses and errors, documenting changes, and testing locally.

They give contributors one place to check the project’s conventions before changing agent-facing code.

How StarGazer1995/mcp-stargazing configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to StarGazer1995/mcp-stargazing. 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/StarGazer1995/mcp-stargazing/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/StarGazer1995/mcp-stargazing

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/stargazer1995/mcp-stargazing/agents-md.svg)](https://agentmods.dev/instructions/stargazer1995/mcp-stargazing/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/stargazer1995/mcp-stargazing/agents-md"><img src="https://agentmods.dev/badge/instructions/stargazer1995/mcp-stargazing/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,141 This file is loaded in full into every session.

When invoked 2,141 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.

Model	Per session	Once invoked
Fable 5.1	$0.02141	$0.02141
Opus 5	$0.01071	$0.01071
Sonnet 5	$0.00428	$0.00428
Haiku 4.5	$0.00214	$0.00214

Measured 7d ago against content hash adc507712558, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp-stargazing 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 7d 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 · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Development Guidelines

This repository exposes MCP tools for AI agents and requires repo-level conventions for safe, consistent agent updates.

See also CLAUDE.md for architecture overview, quick commands, design patterns, known sharp edges, and release process.

Why this file exists

AGENTS.md is the repo-level policy document for:

how new MCP tools are added
how agent-facing interfaces are designed
how the harness validates tool registration and behavior
how changes are documented and tested

This is not a runtime requirement, but it is the best place for team-level regulation.

What belongs here

Tool registration rules
Agent-facing interface design
Response / error formatting requirements
Example and harness test expectations
Deployment and local agent testing workflows

Tool registration conventions

All MCP tools must be defined under src/functions/.
Each tool module must import src.server_instance.mcp and decorate tool entrypoints with @mcp.tool().
The repository should keep tool registration centralized in src/main.py by importing tool modules there.
When explicit @mcp.tool(name=..., description=...) metadata is provided, that metadata takes precedence over the function name and docstring and should be treated as the public contract.
Example domains:
- src/functions/celestial/impl.py
- src/functions/telescope/impl.py
- src/functions/metadata/impl.py
- src/functions/planning/impl.py
- src/functions/weather/impl.py
- src/functions/places/impl.py
- src/functions/time/impl.py

Agent-facing interface rules

All tools must return JSON-serializable data.
Use src.response.format_response(...) for standard response wrapping.
Business validation failures that remain inside normal tool execution should return the structured {error, _meta} payload shape instead of ad hoc dicts.
Dates and times should be returned as ISO strings whenever possible.
Keep tool argument names clear and stable; renames should be treated as breaking changes.
Add new tools only after verifying the new interface is agent-friendly and documented.

Read the full file on GitHub · 171 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.

7d ago First seen · 171 lines · 2,141 tokens per session scan A adc507712558

Subscribe to this mod's changes

mcp-stargazing AGENTS.md is an instructions file published in the GitHub repository StarGazer1995/mcp-stargazing (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,141 tokens to every session, about $0.0107 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.

Building agents

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

mcp-stargazing: Instructions file for Codex