What is unichat-mcp-server AGENTS.md?

Repository instructions for a Python server distributed through PyPI, Python's package repository. They cover cleanup, local commits, and when releases may be published.

Use them when checking the server, removing build leftovers, committing changes, and deciding whether a version change or push is allowed.

They reduce accidental releases and keep generated files, imports, and Git workflow under control.

How amidabuddha/unichat-mcp-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to amidabuddha/unichat-mcp-server. 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/amidabuddha/unichat-mcp-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/amidabuddha/unichat-mcp-server

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/amidabuddha/unichat-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/amidabuddha/unichat-mcp-server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/amidabuddha/unichat-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/amidabuddha/unichat-mcp-server/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/amidabuddha/unichat-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/amidabuddha/unichat-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 441 This file is loaded in full into every session.

When invoked 441 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	$0.00441	$0.00441
Opus 5.5	$0.00176	$0.00176
Sonnet 5.5	$0.00088	$0.00088
Haiku 4.5	$0.00044	$0.00044

Measured 14d ago against content hash c20501bda953, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unichat-mcp-server 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 14d 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 · 22 lines

How it starts

The opening of the file, as written. The whole thing — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository instructions

Closure and clean-up

This MCP server reaches users through PyPI; nothing is installed locally from this checkout. When a change is complete:

Check that it still starts or imports (uv run python -c "import unichat_mcp_server"), then commit locally.
Remove reproducible leftovers: .venv/, __pycache__/, build/, dist/ and *.egg-info/. Keep uv.lock.

For documentation-only changes to repository instructions, review the diff and commit locally; no version bump, dependency installation, build or test run is needed.

Releases

A push to main that changes pyproject.toml triggers .github/workflows/publish.yml, which publishes to PyPI. Change the version, or anything else in pyproject.toml, only when Stefan explicitly asks for a release.
If a published release is broken, violates its compatibility guarantees or contains a security vulnerability, yank the affected release after verifying that the fixed version is available on PyPI. Use the authenticated release-management page at https://pypi.org/manage/project/unichat-mcp-server/releases/ and give a reason naming the defect and the fixed version to upgrade to. Follow PyPI's yanking guidance; preserve the release files and do not yank older releases merely because they have been superseded.
Verify the affected release through https://pypi.org/pypi/unichat-mcp-server/<affected-version>/json: its nonempty urls list must show yanked: true and the intended yanked_reason for every file. Publishing through CI does not establish an authenticated maintainer session for yanking. If authentication blocks it, report the exact versions still pending and do not claim yanking is complete.

Git workflow

Commit locally as work progresses. Push only when Stefan asks; when a milestone is done, ask once whether to push now or not yet.
Use plain git on main. Create branches or pull requests only when asked.

Read the full file on GitHub · 22 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.

14d ago Changed · +4 lines · +233 tokens per session c20501bda953
15d ago First seen · 18 lines · 208 tokens per session scan A 91c7789113bd

Subscribe to this mod's changes

unichat-mcp-server AGENTS.md is an instructions file published in the GitHub repository amidabuddha/unichat-mcp-server (40 stars, last pushed 14d ago), licensed MIT. It adds 441 tokens to every session, about $0.0018 per session on Opus 5.5. 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 2026-10-23.

Commits Git and workflow Languages Python

unichat-mcp-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
unichat-mcp-server AGENTS.mdamidabuddha/unichat-mcp-server	Instructions file	40	14d ago	MIT	A	441	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

unichat-mcp-server: Instructions file for Codex