agentmods.dev

obsidian-transcriber: Instructions file for Codex

AGENTS.md

obsidian-transcriber AGENTS.md is an instructions file for Codex, OpenCode from dsebastien/obsidian-transcriber. It costs 9,035 tokens per session, scanned A, original, MIT.

Repository instructions for Obsidian Transcriber, an Obsidian community plugin written in TypeScript. Obsidian is a note-taking application that can be extended with plugins; the instructions distinguish user documentation from technical project documentation.

In plain words
What is it for?
Use them when modifying main.ts or the plugin build, reading business rules and project history, consulting Obsidian API types, updating the right documentation area, and preparing main.js, manifest.json, or styles.css.
Why use it?
They make clear which files serve end users and which guide developers or coding agents. They also define the required startup reading and release files before changes are made or shipped.

Instructions file for CodexOpenCode

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

This is dsebastien/obsidian-transcriber's own configuration. It tells Codex and OpenCode how to work on obsidian-transcriber 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 obsidian-transcriber configures →

not rated 25repo changed 1mo ago A scan 9,035 tokens original MIT
View source ↗ dsebastien/obsidian-transcriber dsebastien.github.io
Reuse

Borrowing it

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

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 obsidian-transcriber AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dsebastien/obsidian-transcriber/agents-md"><img src="https://agentmods.dev/badge/instructions/dsebastien/obsidian-transcriber/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,035 This file is loaded in full into every session.
When invoked 9,035 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 $0.09035 $0.09035
Opus 5.5 $0.03614 $0.03614
Sonnet 5.5 $0.01807 $0.01807
Haiku 4.5 $0.00903 $0.00903

Measured 1mo ago against content hash 7e1eb43484a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

obsidian-transcriber 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 1mo 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

AGENTS.md · 714 lines

How it starts

The opening of the file, as written. The whole thing — 714 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Documentation

Documentation surfaces

Three locations, do not mix them:

  • README.md — GitHub landing page; pitch, features, install, quick start.
  • docs/ — end-user guide, published via GitHub Pages (Jekyll).
  • documentation/ — technical documentation for you and coding agents (architecture, domain model, business rules, history, plans).

Project overview

  • Target: Obsidian Community Plugin (TypeScript → bundled JavaScript).
  • Entry point: main.ts compiled to main.js and loaded by Obsidian.
  • Required release artifacts: main.js, manifest.json, and optional styles.css.

Agent Workflow

Session-start checklist

Before making any change, read these in order:

  1. documentation/Business Rules.md — mandatory invariants (see below).
  2. The most recent documentation/history/yyyy-mm-dd.md file — what was last done and any open blockers.
  3. Active plans under documentation/plans/ — what the current direction is.
  4. Relevant sections of node_modules/obsidian/obsidian.d.ts whenever you are about to use an Obsidian API you have not recently used. Do not guess API shapes; they change between versions.

Definition of done

A change is only "done" when all of the following hold:

  • bun run tsc passes with zero errors.
  • bun run lint passes with zero warnings (the repo is configured with --max-warnings 0).
  • bun test passes; new logic has new .spec.ts coverage next to the file it tests.
  • bun run build completes without errors.
  • The day's file in documentation/history/ has been updated with what was done, decisions made, and any open questions.
  • If a plan in documentation/plans/ drove the work, it has been updated or closed.
  • Any user-visible change to behavior, commands, or settings is reflected in README.md and/or docs/.

You cannot self-verify UI behavior — Obsidian is a GUI app and agents do not have a live vault. State explicitly in your final message when a change requires manual runtime verification and what to check. Do not claim a UI feature "works" based solely on a passing build.

Read the full file on GitHub · 714 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. 1mo ago Changed · -3 lines · -26 tokens per session 7e1eb43484a7
  2. 1mo ago Changed · +28 lines · +745 tokens per session eedc0cc6c569
  3. 1mo ago Changed · +3 lines · +322 tokens per session 2916175f2a19
  4. 2mo ago First seen · 686 lines · 7,994 tokens per session scan A 8fe582bbcc1c

Subscribe to this mod's changes

obsidian-transcriber AGENTS.md is an instructions file published in the GitHub repository dsebastien/obsidian-transcriber (25 stars, last pushed 25d ago), licensed MIT. It adds 9,035 tokens to every session, about $0.0361 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.

image-processingimage-to-textobsidianobsidian-mdobsidian-pluginocr
Related

obsidian-transcriber AGENTS.md compared with instructions from other repositories

obsidian-transcriber AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
obsidian-transcriber AGENTS.mddsebastien/obsidian-transcriberInstructions file2525d agoMITA9,035Codex, 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