obsidian-local-rest-api AGENTS.md

obsidian-local-rest-api AGENTS.md is an instructions file for Codex, OpenCode from coddingtonbear/obsidian-local-rest-api. It costs 2,334 tokens per session, scanned A, original, MIT.

A contribution guide for an Obsidian plugin that provides a local REST API, meaning HTTP endpoints used to access or control data in Obsidian. It describes small commits, test-first bug fixes, automatic pushes, and unit and integration checks.

In plain words
What is it for?
Use it when fixing bugs, adding tests, changing API endpoints, preparing commits, or deciding when a live Obsidian installation is needed for integration tests.
Why use it?
It keeps each commit working and prevents endpoint changes from being committed without the relevant tests. Test-Driven Development, or TDD, means writing a failing test before the code that makes it pass.

Instructions file for CodexOpenCode

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

About the project

Obsidian Local REST API is a plugin that exposes an Obsidian vault through a secure, authenticated REST API and Model Context Protocol server. Scripts, browser extensions, and AI agents use it to read, search, create, update, and delete notes and other vault files. Its catalogue add-ons provide instructions and settings for using the integration.

coddingtonbear/obsidian-local-rest-api · 2,894 stars · on GitHub · coddingtonbear.github.io

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/coddingtonbear/obsidian-local-rest-api/agents-md
Clone the repo
git clone --depth 1 https://github.com/coddingtonbear/obsidian-local-rest-api

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-local-rest-api AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/coddingtonbear/obsidian-local-rest-api/agents-md.svg)](https://agentmods.dev/instructions/coddingtonbear/obsidian-local-rest-api/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/coddingtonbear/obsidian-local-rest-api/agents-md"><img src="https://agentmods.dev/badge/instructions/coddingtonbear/obsidian-local-rest-api/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,334 This file is loaded in full into every session.
When invoked 2,334 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02334 $0.02334
Opus 5 $0.01167 $0.01167
Sonnet 5 $0.00467 $0.00467
Haiku 4.5 $0.00233 $0.00233

Measured 6d ago against content hash a8913e9dab78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

obsidian-local-rest-api 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 6d 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 · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Commit Process

Commit cadence

Commit frequently in small, self-contained increments. Each commit on main must leave the repository in a working state — no broken builds, no failing unit tests. A commit that fixes a bug, a commit that adds a test, and a commit that updates documentation are all valid atomic units. Do not batch unrelated changes into a single commit.

When working on fixing a bug while on a branch off of main, follow a Test-Driven Development approach and start by creating (and committing) failing tests that will later be fixed by fixes your subsequent commits.

Push Automatically

After making any particular commit, you can feel free to push that branch to the remote.

Running tests before committing

Run the unit test suite before every commit:

npm test

Integration tests require a live Obsidian instance with the plugin's insecure HTTP server enabled and OBSIDIAN_API_KEY set. Run them when Obsidian is available, and always run them before pushing changes that touch endpoint behavior:

npm run test:integration

Two groups of integration tests are skipped by default and opt in via environment variable, because each needs something of the person running them:

  • OBSIDIAN_ACTIVE_FILE=<vault-relative path> — enables the active_file_* tests, which need that file open in Obsidian.
  • OBSIDIAN_TEST_OPEN_FILE=1 — enables the open_file test. It is off by default because opening a file pulls Obsidian to the foreground and takes keyboard focus mid-run, so keystrokes meant for another window can land in the opened note.

Commit message format

Use a plain imperative subject line (no type: prefix). Always include a Co-Authored-By trailer crediting the AI assistant that helped author the commit.

Short imperative description

Longer description of what this work is, why these changes were made, and any decisions, trade-offs, and known limitations that may be useful to future readers.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

Read the full file on GitHub · 196 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. 6d ago First seen · 196 lines · 2,334 tokens per session scan A a8913e9dab78

Subscribe to this mod's changes

obsidian-local-rest-api AGENTS.md is an instructions file published in the GitHub repository coddingtonbear/obsidian-local-rest-api (2,894 stars, last pushed 6d ago), licensed MIT. It adds 2,334 tokens to every session, about $0.0117 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 2026-08-30.

Related

Other instructions, from other repositories

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

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 · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens