agentmods.dev

tabrix: Instructions file for Codex

AGENTS.md

tabrix AGENTS.md is an instructions file for Codex, OpenCode from guodaxia103/tabrix. It costs 1,926 tokens per session, scanned A, original, MIT.

A repository-specific instruction guide for Tabrix AI, covering its development rules, required reading, architecture, and task workflows. Tabrix AI is an application with command-line, MCP, native-server, and diagnostic areas.

In plain words
What is it for?
Use it when changing Tabrix code or documentation, particularly for command-line, MCP, native-server, transport, and diagnostics work.
Why use it?
It tells coding agents how to make small, verifiable changes that follow the project’s contribution rules and avoid regressions.

Instructions file for CodexOpenCode

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

This is guodaxia103/tabrix's own configuration. It tells Codex and OpenCode how to work on tabrix 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 tabrix configures →

not rated 5repo changed 29d ago A scan 1,926 tokens original MIT
View source ↗ guodaxia103/tabrix
Reuse

Borrowing it

Nothing to install: this file belongs to guodaxia103/tabrix. 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/guodaxia103/tabrix/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/guodaxia103/tabrix

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 tabrix AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/guodaxia103/tabrix/agents-md/github.svg)](https://agentmods.dev/instructions/guodaxia103/tabrix/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/guodaxia103/tabrix/agents-md"><img src="https://agentmods.dev/badge/instructions/guodaxia103/tabrix/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 tabrix AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/guodaxia103/tabrix/agents-md"><img src="https://agentmods.dev/badge/instructions/guodaxia103/tabrix/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,926 This file is loaded in full into every session.
When invoked 1,926 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 $0.01926 $0.01926
Opus 5.5 $0.00770 $0.00770
Sonnet 5.5 $0.00385 $0.00385
Haiku 4.5 $0.00193 $0.00193

Measured 29d ago against content hash d9162bb3edbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tabrix 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 29d 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 · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tabrix AI Contributor Rules

Tabrix accepts contributions from any AI coding assistant. The assistant name does not matter; the responsibility and evidence standard do.

Tabrix's public product center is:

real Chrome + MCP control + browser object awareness + memory and reuse

Do not turn Tabrix back into a workflow SaaS, embedded assistant UI, visual editor, local semantic-search stack, or site-specific automation product.

Before Editing

Before changing files, confirm the checkout and dirty state:

git rev-parse --show-toplevel
git status --short --branch

If the user names a path such as E:\projects\AI\codex\main_tabrix, edit that checkout, not a sibling clone or temporary worktree.

Read the public docs in this order for non-trivial work:

  1. README.md
  2. docs/README.md
  3. docs/ROADMAP.md
  4. docs/PRODUCT_SURFACE_MATRIX.md
  5. docs/ARCHITECTURE.md
  6. docs/PROJECT_STRUCTURE.md
  7. CONTRIBUTING.md

Then read only the task-relevant docs:

Product Boundary

Current public layers:

  • Object: current and learned browser-page summaries, lifecycle state, page objects, actionable targets, source/API clues, freshness.
  • Memory: AI-to-Tabrix tool-call records, request/response summaries, target page context, timing, failures, and AI feedback. Memory must not invent or substitute AI evaluation.
  • Knowledge: privacy-safe page/source capability summaries distilled from Object records.
  • Experience: reusable operation paths distilled only from AI-reviewed successful Memory records.
  • Policy: source choice, freshness gates, risk gates, fallback constraints, and execution constraints.

Read the full file on GitHub · 204 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. 29d ago Changed · -61 lines · -3,337 tokens per session d9162bb3edbe
  2. 2mo ago First seen · 265 lines · 5,263 tokens per session scan A bc63f8675648

Subscribe to this mod's changes

tabrix AGENTS.md is an instructions file published in the GitHub repository guodaxia103/tabrix (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,926 tokens to every session, about $0.0077 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 2026-08-31.

LLMai-agentsbrowser-automationchrome-extensionllm-toolsmcp
Related

tabrix AGENTS.md compared with instructions from other repositories

tabrix AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tabrix AGENTS.mdguodaxia103/tabrixInstructions file51mo agoMITA1,926Codex, 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