console-chat-gpt: Instructions file for Codex

AGENTS.md

console-chat-gpt AGENTS.md is an instructions file for Codex, OpenCode from amidabuddha/console-chat-gpt. It costs 412 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for the amidabuddha/console-chat-gpt project, covering focused commits, versioning, formatting, changelogs, and pushing code. A commit is a saved set of code changes, while a changelog records notable updates.

In plain words
What is it for?
Use them when preparing commits, updating versions or changelogs, checking staged changes, and pushing to main.
Why use it?
They reduce accidental mixing of unrelated changes and explain what happens when code is pushed to the main branch.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is amidabuddha/console-chat-gpt's own configuration. It tells Codex and OpenCode how to work on console-chat-gpt 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 console-chat-gpt configures →

Reuse

Borrowing it

Nothing to install: this file belongs to amidabuddha/console-chat-gpt. 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/console-chat-gpt/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/amidabuddha/console-chat-gpt

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 console-chat-gpt AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/amidabuddha/console-chat-gpt/agents-md/github.svg)](https://agentmods.dev/instructions/amidabuddha/console-chat-gpt/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/amidabuddha/console-chat-gpt/agents-md"><img src="https://agentmods.dev/badge/instructions/amidabuddha/console-chat-gpt/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 console-chat-gpt AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/amidabuddha/console-chat-gpt/agents-md"><img src="https://agentmods.dev/badge/instructions/amidabuddha/console-chat-gpt/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 412 This file is loaded in full into every session.
When invoked 412 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 $0.00412 $0.00412
Opus 5.5 $0.00165 $0.00165
Sonnet 5.5 $0.00082 $0.00082
Haiku 4.5 $0.00041 $0.00041

Measured 15d ago against content hash b4331dc6b82c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

console-chat-gpt 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 15d 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 · 23 lines

What it actually says

Repository Instructions

Commit Hygiene

  • Keep commits scoped to one behavioral change. Do not bundle separate features, bug fixes, formatting-only changes, or experiments into the same commit.
  • Before committing, inspect the staged diff and split it when the change contains distinct user-visible outcomes. For example, Telegram rich formatting and Telegram streaming should be separate commits.
  • Use the versioning prefix convention from app-data/bump-version.sh: [Feature], [Improvement], or [Bugfix].
  • Keep automatic changelog/version/formatting commits separate from functional commits unless the user explicitly asks to combine them.
  • If an exploratory change is abandoned or reverted before commit, remove the related code and documentation before committing the remaining work.

Closure and clean-up

  • The app runs from this checkout (main.py), and its data lives here too: app-data/, chats/, assistants/, roles/, images/, config.toml, mcp_config.json and remote_mcp_config.json. Never delete them. Nothing is installed elsewhere.
  • When a change is complete, commit it locally, then remove only reproducible leftovers such as __pycache__/ directories and node_modules/.

Push 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.

  • Every push to main triggers .github/workflows/formatting.yml, which may push a follow-up commit named Formatting and updating the changelog. that updates formatting, CHANGELOG.md, and app-data/version.toml.

  • Before pushing to main, fetch origin/main and rebase local commits if the remote branch has advanced. Never force-push merely to bypass the automation commit.

  • After pushing to main, wait for the formatting workflow to finish, then fetch and fast-forward the local branch so the checkout includes the generated commit before starting or pushing more work.

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. 15d ago Changed · +7 lines · +137 tokens per session b4331dc6b82c
  2. 2mo ago First seen · 16 lines · 275 tokens per session scan A 7c96c2cac380

Subscribe to this mod's changes

console-chat-gpt AGENTS.md is an instructions file published in the GitHub repository amidabuddha/console-chat-gpt (158 stars, last pushed 10d ago), licensed Apache-2.0. It adds 412 tokens to every session, about $0.0016 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.

Related

console-chat-gpt AGENTS.md compared with instructions from other repositories

console-chat-gpt AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
console-chat-gpt AGENTS.mdamidabuddha/console-chat-gptInstructions file15810d agoApache-2.0A412Codex, 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