BloomDesktop: Instructions file for Codex

AGENTS.md

BloomDesktop AGENTS.md is an instructions file for Codex, OpenCode from BloomBooks/BloomDesktop. It costs 2,503 tokens per session, scanned A, original, MIT.

Project instructions for BloomDesktop, a desktop application with a C# backend, a React and TypeScript front end, and an embedded web view. They describe the project's architecture, coding rules, branch target, and testing practices.

In plain words
What is it for?
Use them when changing BloomDesktop code, its front end, its C# backend, or its reading-app build tests.
Why use it?
They give an agent the project-specific rules needed to make compatible changes and run the right checks.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is BloomBooks/BloomDesktop's own configuration. It tells Codex and OpenCode how to work on BloomDesktop 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 BloomDesktop configures →

Reuse

Borrowing it

Nothing to install: this file belongs to BloomBooks/BloomDesktop. 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/BloomBooks/BloomDesktop/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/BloomBooks/BloomDesktop

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 BloomDesktop AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bloombooks/bloomdesktop/agents-md"><img src="https://agentmods.dev/badge/instructions/bloombooks/bloomdesktop/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,503 This file is loaded in full into every session.
When invoked 2,503 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 $0.02503 $0.02503
Opus 5.5 $0.01001 $0.01001
Sonnet 5.5 $0.00501 $0.00501
Haiku 4.5 $0.00250 $0.00250

Measured 7d ago against content hash 09037e985fed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

BloomDesktop 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 7d 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 · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This project has a web front-end at src/BloomBrowserUI. The front-end uses pnpm 11.5.2. Never ever use npm or yarn.

Architecture

  • C# backend
  • web front-end in React/Typescript
  • WebView2 for hosting the web front-end in the desktop app
  • We strictly control both ends of the API.
    • Don't worry about legacy API support. If you need to change the API, just change it on both sides.
    • Don't be overly defensive about error handling. If the API is used incorrectly, it's fine for it to throw an error. We want to know about it so we can fix it.

Code Style

  • React components are arrow function components (see the example below); src/BloomBrowserUI/AGENTS.md covers other functions

  • do not destructure props

  • do not define a props data type unless it is huge

  • example: export const SomeComponent: React.FunctionComponent<{initiallySelectedGroupIndex: number;}> = (props) => {...}

  • Avoid removing existing comments unless your changes make them inaccurate/obsolete

  • Avoid adding a comment like "// add this line".

  • Style elements using the css macro from @emotion/react directly on the element being styled, using the css prop. E.g. <div css={csscolor:red}>

  • Where possible style things using @emotion/react rather than using sx objects.

  • Avoid stacking/nesting ternary (? :) operators (e.g. a ? x : b ? y : z). They're too hard for humans to read. Use an if/else-if chain (or a switch) instead. A single, non-nested ternary is fine.

  • For Typescript coding style, see ./src/BloomBrowserUI/AGENTS.md

Testing

  • Fail Fast. Don't write code that silently works around failed dependencies. If a dependency is missing we should fail. Javascript itself will fail if we try to use a missing dependency, and that's fine. E.g. if you expect a foo to be defined, don't write "if(foo){}". Just use foo and if it's null, fine, we'll get an error, which is good.
  • Try to make it so that test failures indicate what went wrong. For example, fail("An error occurred in setup; we should not have gotten here") would be better than expect(false).toBeTruthy(); and expect(foo).toBe(3); would be better than expect(foo === 3).toBe(true);.
  • Add sanity checks to guard against falsely passing tests. For example, when unit testing a method, sanity check that the test data values are as expected before you call the method, and then after you call the method you can verify that those values have changed as expected.
  • Never accept a flaky test. A test that fails without a code change to explain it is flaky from its first failure; it is reporting a real race, in Bloom or in the test: find out which and fix the cause. Waiting to see whether it fails again is accepting it. Any way of working around the flakiness instead (retries, re-running until it passes, waiting to see if it recurs, a longer timeout, a fixed delay, looser assertions, skipping the test, a test hook added to Bloom) needs the developer's permission first.
  • Nightly CI failures: docs/nightly-failures/README.md records what is already known about each one. To look at recent nightlies, follow .claude/skills/nightly-triage/SKILL.md, which keeps that doc up to date.

Read the full file on GitHub · 139 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. 7d ago Changed · +6 lines · +151 tokens per session 09037e985fed
  2. 22d ago Changed · +31 tokens per session 587ff9470653
  3. 23d ago Changed · +13 lines · +199 tokens per session c1a599dc024c
  4. 27d ago Changed · +1 lines · +58 tokens per session 1a23b611d02a
  5. 1mo ago Changed · +81 tokens per session afc790ead825
  6. 1mo ago Changed · -13 lines · -78 tokens per session 4f7d5c1371b3
  7. 1mo ago Changed · +9 lines · +127 tokens per session 3641dff132e7
  8. 1mo ago Changed · -3 lines · -78 tokens per session db21e8506e57
  9. 1mo ago Changed · +4 lines · +39 tokens per session 7bb764842e21
  10. 1mo ago First seen · 122 lines · 1,973 tokens per session scan A 43d6941aab59

Subscribe to this mod's changes

BloomDesktop AGENTS.md is an instructions file published in the GitHub repository BloomBooks/BloomDesktop (43 stars, last pushed today), licensed MIT. It adds 2,503 tokens to every session, about $0.0100 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.

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 · 9,715 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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens