What is autodoubao AGENTS.md?

A repository-specific instruction file for the AutoDoubao project, which connects coding agents to a local MCP bridge and Doubao’s logged-in web session. It records required documents, browser constraints, image retrieval rules, and verification steps.

Guiding work on AutoDoubao browser automation, MCP calls, image generation jobs, network interception, client configuration, and related troubleshooting.

It gives agents the project context and safeguards needed to change or troubleshoot the bridge without using the wrong image source or skipping required checks.

How linxxcat000/autodoubao configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to linxxcat000/autodoubao. 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/linxxcat000/autodoubao/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/linxxcat000/autodoubao

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/linxxcat000/autodoubao/agents-md/github.svg)](https://agentmods.dev/instructions/linxxcat000/autodoubao/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/linxxcat000/autodoubao/agents-md"><img src="https://agentmods.dev/badge/instructions/linxxcat000/autodoubao/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/linxxcat000/autodoubao/agents-md"><img src="https://agentmods.dev/badge/instructions/linxxcat000/autodoubao/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 667 This file is loaded in full into every session.

When invoked 667 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	$0.00667	$0.00667
Opus 5	$0.00333	$0.00333
Sonnet 5	$0.00133	$0.00133
Haiku 4.5	$0.00067	$0.00067

Measured 8d ago against content hash 7de6438f9505, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

autodoubao 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 8d 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 · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoDoubao project instructions

Durable context

This repository implements a local MCP bridge shared by Codex, Hermes Agent, and LobsterAI. It uses the user's logged-in Doubao web session and does not call a paid image-generation API.
Read docs/AUTODOUBAO_IMPLEMENTATION_ZH.md before changing browser automation, image acquisition, client configuration, or troubleshooting behavior.
The verified extension architecture is version 0.2.0: reliable composer submission in extension/content.js, followed by CDP Network interception in extension/background.js and extraction of image_ori_raw / image_raw URLs.
Never revert normal image acquisition to DOM <img> scraping. DOM width/height attributes and src/srcset can represent a 384x216 preview even when the requested and original image is 2848x1600.
Do not try to derive an original URL by removing ImageX query parameters or editing signed URLs.

Using the MCP

MCP URL: http://127.0.0.1:8878/mcp.
Call doubao_status first. Require both browser_connected and doubao_page_ready before generating.
Call doubao_generate once, retain its job_id, and poll doubao_job_status every 3-5 seconds. Do not enqueue duplicates while waiting.
On completion, inspect the returned absolute image path, verify actual pixel dimensions, and visually assess the asset before placing it into a game.
If an image is unsuitable, describe observable defects and make a targeted new prompt. Do not silently retry login, captcha, quota, rate-limit, or attention_required states.
output_subdir is relative to the configured output root. Copy an accepted asset into another project only when that action is within the user's request.

Browser constraints

The extension requires Chrome's debugger permission and attaches only during an active job. Do not open DevTools on the controlled Doubao tab during a job.
The user signs in manually. Never store credentials, clear cookies, bypass quotas, or attempt to solve security verification.
Signed original-image URLs should be downloaded immediately; do not persist them as durable artifacts.
If Doubao changes, diagnose the failing layer first: MCP, WebSocket, page readiness, prompt submission, generation, network parsing, download, or file handoff. Do not bump the extension version until a tested behavior change exists.

Read the full file on GitHub · 54 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.

8d ago First seen · 54 lines · 667 tokens per session scan A 7de6438f9505

Subscribe to this mod's changes

autodoubao AGENTS.md is an instructions file published in the GitHub repository linxxcat000/autodoubao (1 stars, last pushed 25d ago), licensed MIT. It adds 667 tokens to every session, about $0.0033 per session on Opus 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.

browser-automation codex doubao hermes-agent image-generation mcp

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

autodoubao: Instructions file for Codex