What is chatgpt-md AGENTS.md?

Project instructions for developing the chatgpt-md Obsidian plugin, which brings language-model workflows into Markdown notes.

Use them when modifying the plugin, especially its TypeScript entry point, services, settings, commands, tests, builds, or lint checks.

They give a coding agent the project context and validation commands needed to make changes that fit the existing architecture.

How bramses/chatgpt-md configures Codex and OpenCode

About the project

ChatGPT MD is an Obsidian plugin that lets users chat with AI inside their notes, reference notes through wiki links, and optionally let the AI search the vault, read notes, or browse the web with approval. It is for writers and developers who want cloud or locally hosted AI assistance while keeping their work in an Obsidian vault. The catalogue entries provide instructions for using the plugin.

bramses/chatgpt-md · 1,456 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to bramses/chatgpt-md. 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/bramses/chatgpt-md/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/bramses/chatgpt-md

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/bramses/chatgpt-md/agents-md/github.svg)](https://agentmods.dev/instructions/bramses/chatgpt-md/agents-md)

Your own site

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

Per session 2,130 This file is loaded in full into every session.

When invoked 2,130 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	$0.02130	$0.02130
Opus 5.5	$0.00852	$0.00852
Sonnet 5.5	$0.00426	$0.00426
Haiku 4.5	$0.00213	$0.00213

Measured 2mo ago against content hash 40463348e0b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chatgpt-md 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 · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

AI coding-agent instructions for chatgpt-md.

Project overview

chatgpt-md is an Obsidian community plugin that brings LLM workflows into markdown notes. It supports:

Chat interactions directly inside Obsidian notes.
Multiple providers: OpenAI, OpenRouter, Anthropic, Gemini, Ollama, LM Studio, Z.AI, and compatible APIs.
Per-note configuration through YAML frontmatter.
Streaming responses.
Human-approved AI tool calls for vault and web search workflows.

The plugin is TypeScript, bundled by esbuild, and runs inside the Obsidian plugin runtime.

Validation commands

Use npm for validation unless the project explicitly changes package-manager policy.

npm run build
npm test -- --runInBand
npm run lint

Lint runs the official Obsidian plugin rules via eslint-plugin-obsidianmd. Expected state: 0 errors and a small set of known warnings (untyped tool results in ToolService, the prefer-setting-definitions nudge). Do not add new warnings; do not treat the known ones as task blockers. no-unsupported-api cannot be disabled inline — it validates every API call against minAppVersion in manifest.json.

Compatibility floor and dependency pins

minAppVersion is 1.11.4, pinned by the SecretStorage/SecretComponent credential APIs (ApiAuthService). Copilot uses the same floor.
The obsidian devDependency is pinned to the same 1.11.4 so tsc enforces the floor alongside the lint rule. Never set it back to latest.
@codemirror/state (6.5.0) and @codemirror/view (6.38.6) must stay exact: obsidian declares them as exact peers.
typescript is 6.x latest (<6.1.0): TypeScript 7 is blocked by @typescript-eslint peer ranges.
When raising minAppVersion, update the obsidian typings pin in the same change.

Releasing

Merge work to master, validate (npm test -- --runInBand, npm run build).
node update-version.mjs <x.y.z> — updates package.json, manifest.json, versions.json, commits, and tags.
Push master and the tag.
Create the GitHub release with the three Obsidian-required assets: main.js, manifest.json, styles.css. versions.json gates updates so users on older Obsidian stay on the last compatible release.

Read the full file on GitHub · 214 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 Changed · +20 lines · +578 tokens per session 40463348e0b1
2mo ago First seen · 194 lines · 1,552 tokens per session scan A 0a1343de6018

Subscribe to this mod's changes

chatgpt-md AGENTS.md is an instructions file published in the GitHub repository bramses/chatgpt-md (1,456 stars, last pushed 2mo ago), licensed MIT. It adds 2,130 tokens to every session, about $0.0085 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.

chatgpt-md AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
chatgpt-md AGENTS.mdbramses/chatgpt-md	Instructions file	1.5k	2mo ago	MIT	A	2,130	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	today	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

chatgpt-md: Instructions file for Codex