What is all-in-obs AGENTS.md?

Project instructions for maintaining an Obsidian plugin that imports content from Xiaohongshu and WeChat, two Chinese content platforms.

Use them when debugging short-link redirects, HTML extraction, or final import errors, especially in the plugin's Xiaohongshu services.

They provide a standard way to reproduce import failures, inspect logs, locate the failing stage, and check that fixes do not cause regressions.

How hztBUAA/all-in-obs configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to hztBUAA/all-in-obs. 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/hztBUAA/all-in-obs/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hztBUAA/all-in-obs

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/hztbuaa/all-in-obs/agents-md/github.svg)](https://agentmods.dev/instructions/hztbuaa/all-in-obs/agents-md)

Your own site

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

Per session 745 This file is loaded in full into every session.

When invoked 745 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	$0.00745	$0.00745
Opus 5.5	$0.00298	$0.00298
Sonnet 5.5	$0.00149	$0.00149
Haiku 4.5	$0.00075	$0.00075

Measured 2mo ago against content hash fe219daa4575, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

all-in-obs 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 2mo 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.

AGENTS Workflow

This repository uses a reproducible fix loop for Xiaohongshu and WeChat import issues.

Standard Debug Loop

Reproduce with real plugin entry:

In Obsidian command palette, run 运行多平台实网 Smoke 测试.
Or run from plugin settings page using one-click smoke buttons.
This calls the same service path used by normal import flow (main.ts -> XhsResolver/XhsNoteService).

Inspect artifacts:

Debug log: .obsidian/plugins/multi-source-content-importer/debug.log
Smoke report: .obsidian/plugins/multi-source-content-importer/smoke-report.json

Locate failure stage from logs:

resolve-get-response / resolve-head-response: shortlink redirect behavior.
resolve-html-extracted: HTML fallback extraction behavior.
import-error: final user-facing failure reason.

Implement minimal fix:

Prefer fixing src/platforms/xhs/* service modules.
Keep plugin shell orchestration in main.ts.

Regression run:

Re-run smoke command.
Ensure no case regresses compared with baseline.

Baseline XHS Smoke Cases

http://xhslink.com/o/AOCPqBZcRZ8
http://xhslink.com/o/9mieTWxY9ce
http://xhslink.com/o/vwCTLUg3W5
http://xhslink.com/o/9WJrnkkjpx5
http://xhslink.com/o/8glUzkSMrIo

WeChat Smoke Cases

Maintained in src/platforms/wechat/smoke-cases.ts.
Default list can be empty because WeChat may intermittently return verification pages by network.
Users can override both platform smoke cases from plugin settings (one case per line).

Architecture Boundaries

main.ts
Plugin shell: commands, settings, orchestration.
src/plugin
import-modal.ts: import input UI.
settings-tab.ts: plugin settings UI.
folder-suggest.ts: folder path suggestions.
types.ts: plugin-level settings/input contracts.
platform-smoke.ts: unified real-network smoke runner for wechat/xiaohongshu.
src/platforms/xhs
resolver.ts: shortlink resolution (GET Location -> HEAD Location -> HTML extraction -> token rebuild).
note-service.ts: note HTML fetch, unavailable-page detection, structured extraction.
smoke-cases.ts: shared real-world smoke case set.

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.

2mo ago First seen · 79 lines · 745 tokens per session scan A fe219daa4575

Subscribe to this mod's changes

all-in-obs AGENTS.md is an instructions file published in the GitHub repository hztBUAA/all-in-obs (60 stars, last pushed 6mo ago), licensed MIT. It adds 745 tokens to every session, about $0.0030 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.

all-in-obs AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
all-in-obs AGENTS.mdhztBUAA/all-in-obs	Instructions file	60	6mo ago	MIT	A	745	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	yesterday	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

all-in-obs: Instructions file for Codex