agentmods.dev

chibi: Instructions file for Codex

AGENTS.md

chibi AGENTS.md is an instructions file for Codex, OpenCode from s-nagaev/chibi. It costs 4,017 tokens per session, scanned A, original, MIT.

A set of AGENTS.md instructions for the Chibi codebase, an open-source self-hosted Telegram bot that coordinates AI providers, tools, integrations, and sub-agents. It defines project structure and Python coding rules.

In plain words
What is it for?
Use it when an agent edits Chibi code, especially Python backend files, docstrings, configuration, or other parts of the documented project layout.
Why use it?
It gives coding agents a shared source of truth for how to change this repository without violating its conventions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

This is s-nagaev/chibi's own configuration. It tells Codex and OpenCode how to work on chibi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything chibi configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/sergio/Develop/personal/chibi/.

not rated 54repo +1 changed 5d ago A scan 4,017 tokens original MIT
View source ↗ s-nagaev/chibi chibi.bot
Reuse

Borrowing it

Nothing to install: this file belongs to s-nagaev/chibi. 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/s-nagaev/chibi/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/s-nagaev/chibi

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.

agentmods badge for chibi AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/s-nagaev/chibi/agents-md/github.svg)](https://agentmods.dev/instructions/s-nagaev/chibi/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/s-nagaev/chibi/agents-md"><img src="https://agentmods.dev/badge/instructions/s-nagaev/chibi/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.

agentmods 80×15 button for chibi AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/s-nagaev/chibi/agents-md"><img src="https://agentmods.dev/badge/instructions/s-nagaev/chibi/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,017 This file is loaded in full into every session.
When invoked 4,017 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04017 $0.04017
Opus 5.5 $0.01607 $0.01607
Sonnet 5.5 $0.00803 $0.00803
Haiku 4.5 $0.00402 $0.00402

Measured 5d ago against content hash 3f2960ce8643, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chibi 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.

AGENTS.md · 328 lines

How it starts

The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — AI Agent Guidelines for Chibi

Purpose: This document defines how AI agents (executors, reviewers, planners) MUST work within the Chibi codebase. It is the single source of truth for code conventions, tooling, and project structure.

Precedence: On conflict, AGENTS.md governs code conventions; workflow skills (executor_workflow_skill.md, reviewer_workflow_skill.md) govern process. If they disagree on process, the skill wins; on code style and architecture, AGENTS.md wins.

1. Project Identity

Chibi — open-source, self-hosted Telegram bot (MIT License). Orchestrates multiple AI providers, tools, MCP integrations, and sub-agents for autonomous task execution. Built with python-telegram-bot v22.7+, Pydantic v2, Redis, DynamoDB.

  • Repository: https://github.com/s-nagaev/chibi
  • Docs: https://chibi.bot
  • Package: chibi-bot on PyPI
  • Docker: pysergio/chibi on Docker Hub
  • Python: ^3.11

2. Directory Layout

chibi/                    # Main package
├── __main__.py           # `python -m chibi` entry point
├── cli.py                # CLI (Click)
├── config/               # Settings: app, gpt, telegram, logging
│   └── __init__.py       # Exports singletons: application/gpt/telegram_settings
├── constants.py          # Enums, constants, provider metadata
├── exceptions.py         # Custom exceptions
├── models.py             # Pydantic models (User, Message, etc.)
├── interfaces/           # Interface protocols: interface.py (UserInterface,
│   │                     # EditorContextProvider), telegram_interface.py
│   │                     # (TelegramInterface), terminal_interface.py,
│   │                     # scheduler_interface.py,
│   │                     # stdio_interface.py (StdioInterface),
│   │                     # stdio_runner.py (StdioRunner)
├── runners/              # Entry points: telegram.py, terminal.py
├── schemas/              # Provider API request/response schemas (Pydantic)
├── service.py            # Core service orchestration
├── services/             # Business logic
│   ├── events/           # Event modules: cwd_events.py, subagent_events.py
│   ├── providers/        # LLM provider adapters
│   │   └── tools/        # ChibiTools exposed to LLMs
│   └── ...
├── storage/              # Persistence: redis.py, dynamodb.py, local.py, database.py (factory)
└── utils/                # Utility functions
data/                     # Runtime data & skills
docs/                     # Documentation
scripts/                  # Operational scripts
tests/                    # pytest suite
.project/                 # PM workflow artifacts (not packaged)
conftest.py               # Shared pytest fixtures
pyproject.toml            # Poetry config + tool settings

Read the full file on GitHub · 328 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.

  1. 5d ago Changed · +7 lines · +99 tokens per session 3f2960ce8643
  2. 12d ago First seen · 321 lines · 3,918 tokens per session scan A 4992b0049794

Subscribe to this mod's changes

chibi AGENTS.md is an instructions file published in the GitHub repository s-nagaev/chibi (54 stars, last pushed 2d ago), licensed MIT. It adds 4,017 tokens to every session, about $0.0161 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 2026-10-26.

Building agentsanthropicchatbotclaudedockerraspberry-piself-hosted
Related

chibi AGENTS.md compared with instructions from other repositories

chibi AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
chibi AGENTS.mds-nagaev/chibiInstructions file542d agoMITA4,017Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode