What is hermes-tweet AGENTS.md?

Repository instructions for Hermes Tweet, a plugin that supports automation on X, formerly known as Twitter. They define commands, strict source-code rules, checks, tests, security reviews, and release requirements.

Use them when editing code, running formatting and type checks, testing, auditing dependencies, checking compatibility, or preparing a package release.

They turn the project’s quality and release expectations into explicit checks, including a rule that every commit must reduce handwritten source code overall.

How Xquik-dev/hermes-tweet configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Xquik-dev/hermes-tweet. 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/Xquik-dev/hermes-tweet/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Xquik-dev/hermes-tweet

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/xquik-dev/hermes-tweet/agents-md/github.svg)](https://agentmods.dev/instructions/xquik-dev/hermes-tweet/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/xquik-dev/hermes-tweet/agents-md"><img src="https://agentmods.dev/badge/instructions/xquik-dev/hermes-tweet/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/xquik-dev/hermes-tweet/agents-md"><img src="https://agentmods.dev/badge/instructions/xquik-dev/hermes-tweet/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 787 This file is loaded in full into every session.

When invoked 787 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	$0.00787	$0.00787
Opus 5.5	$0.00315	$0.00315
Sonnet 5.5	$0.00157	$0.00157
Haiku 4.5	$0.00079	$0.00079

Measured 2d ago against content hash 453a3d3dc65f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hermes-tweet 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 2d 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 · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide for Hermes Tweet

This file tells coding agents how to change this repository. Hermes Tweet is a Hermes Agent plugin for X (Twitter) search and approved X actions.

Know the layout

plugin.yaml and hermes_tweet/plugin.yaml describe the plugin to Hermes. Keep them identical.
hermes_tweet/__init__.py registers the 3 tools, the 2 slash commands and the bundled Skill.
hermes_tweet/tools.py runs tweet_explore, tweet_read and tweet_action.
hermes_tweet/client.py sends each request to the Xquik API.
scripts/build_catalog.py writes the endpoint catalog to hermes_tweet/catalog_data.json.
skills/hermes-tweet/ and hermes_tweet/skills/hermes-tweet/ hold the bundled Skill. Keep both copies identical.
.claude-plugin/plugin.json and .codex-plugin/plugin.json describe the plugin to Claude Code and Codex.
tests/ holds the pytest suite. scripts/ holds the check scripts.

Set up

Install the locked dependencies on Python 3.12.

uv sync --locked --python 3.12 --group dev

Run the checks

bin/check-local runs every check a change must pass. Run it before you open a pull request.

bin/check-local --no-status

Without --no-status, it posts a commit status for a clean, pushed commit.

Run single checks while you work.

uv run ruff format --check .
uv run ruff check --ignore-noqa .
uv run basedpyright
uv run mypy
uv run pytest --cov=hermes_tweet --cov=tests --cov-report=term-missing --cov-fail-under=100
uv run python scripts/check_public_safety.py
uv run python scripts/check_license_headers.py
uv run bandit -c pyproject.toml -r hermes_tweet scripts fuzz
uv run pip-audit
bash scripts/plugin-scan

Regenerate the catalog after the OpenAPI schema changes.

uv run python scripts/build_catalog.py /path/to/openapi.yaml

Follow the code rules

Ruff runs every rule. Fix each finding, because --ignore-noqa voids noqa comments.
basedpyright and mypy run in strict mode. Never use typing.Any or typing.cast.
The build rejects type: ignore, mypy: and pyright: comments.
Tests cover 100% of hermes_tweet and tests. Add a test for each code change.
Start each Python, shell, TOML and YAML file with the 2 SPDX lines the other files carry.
Change dependencies in pyproject.toml, then run uv lock.

Read the full file on GitHub · 79 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.

2d ago Changed · +29 lines · +210 tokens per session 453a3d3dc65f
2mo ago First seen · 50 lines · 577 tokens per session scan A bdfb0fada817

Subscribe to this mod's changes

hermes-tweet AGENTS.md is an instructions file published in the GitHub repository Xquik-dev/hermes-tweet (37 stars, last pushed yesterday), licensed MIT. It adds 787 tokens to every session, about $0.0031 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 2026-08-30.

Python agent-tools ai-agent hermes-agent twitter x-api

hermes-tweet AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hermes-tweet AGENTS.mdXquik-dev/hermes-tweet	Instructions file	37	yesterday	MIT	A	787	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	today	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

hermes-tweet: Instructions file for Codex