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.
npx agentmods add instructions/opspresso/vibemon-app/agents-mdgit clone --depth 1 https://github.com/opspresso/vibemon-appWrote 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.
[](https://agentmods.dev/instructions/opspresso/vibemon-app/agents-md)<a href="https://agentmods.dev/instructions/opspresso/vibemon-app/agents-md"><img src="https://agentmods.dev/badge/instructions/opspresso/vibemon-app/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00802 | $0.00802 |
| Opus 5 | $0.00401 | $0.00401 |
| Sonnet 5 | $0.00160 | $0.00160 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
vibemon-app 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
VibeMon is an Electron desktop application. The main process starts in src/main.js; CommonJS services live in src/modules/, shared registries in src/shared/, and renderer code in src/renderer.js, src/bubble/, and src/engine/. Keep tests in tests/, documentation in docs/, CLI code in bin/, character art in src/assets/characters/, and application icons in assets/.
Architecture & Data Flow
HTTP and WebSocket updates converge at routeStatusUpdate() and flow through CharacterWindowManager to one retargetable character window and speech bubble. Preserve this ingress and focus-selection behavior. State and character registries and the rendering modules are canonical in vibemon-static; update them there, then sync the copies with pnpm check:registry -- --fix. Keep timeouts and sizes in src/shared/data/constants.json (_MS for milliseconds). The renderer CSP requires local Three.js files; do not use runtime CDN imports — src/renderer.js passes the vendored three.js namespace to the 3D engine as options.THREE.
Build, Test, and Development Commands
Use pnpm:
pnpm installinstalls dependencies.pnpm startlaunches the Electron app locally.pnpm lintchecks JavaScript and CommonJS files with ESLint.pnpm testruns the Jest suite once;pnpm test:watchreruns affected tests during development.pnpm test:coveragewrites coverage reports tocoverage/.pnpm buildcreates platform packages without publishing. Usepnpm build:mac,pnpm build:win, orpnpm build:linuxfor a specific target.pnpm check:registrycompares the bundled registry data, character art, and vendored rendering modules againstvibemon-static(-- --fixoverwrites the local copies;VIBEMON_STATIC_DIR=../vibemon-staticcompares against a local checkout instead of GitHub).
Coding Style & Naming Conventions
Follow eslint.config.js: two-space indentation, single quotes, semicolons, no trailing commas, and an ending newline. Use camelCase for variables and functions, PascalCase for classes, and kebab-case filenames such as state-manager.cjs. Preserve module boundaries: main-process modules use CommonJS (.cjs), while renderer and engine code may use ES modules. Do not edit files under src/vendor/. src/engine/, src/bubble/, src/shared/data/{states,characters}.json, and src/assets/characters/ are verbatim copies of vibemon-static: change them there and re-sync, never in place — CI compares them against the canonical copies.
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.
- 4d ago First seen · 38 lines · 802 tokens per session scan A 7247adb3c64e
vibemon-app AGENTS.md is an instructions file published in the GitHub repository opspresso/vibemon-app (23 stars, last pushed 9d ago), licensed MIT. It adds 802 tokens to every session, about $0.0040 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.
Other instructions, from other repositories
vscode tree-widgets.instructions.md
Use when asked to consume workbench tree widgets in VS Code.
vscode accessibility.instructions.md
Use when implementing accessibility features, ARIA labels, screen reader support, accessible help dialogs, or keybinding scoping for accessibility. Covers AccessibleContentProvider, CONTEXTACCESSIBILITYMODEENABLED, verbosity settings, and announcement patterns.
vscode writing-tests.instructions.md
VS Code test writing guidelines — unit tests, integration tests, snapshot tests, and clean teardown patterns. Reference when writing or updating tests.
vscode interactive.instructions.md
Architecture documentation for VS Code interactive window component. Use when working in src/vs/workbench/contrib/interactive.
vscode notebook.instructions.md
Architecture documentation for VS Code notebook and interactive window components. Use when working in src/vs/workbench/contrib/notebook/.
vscode chat.instructions.md
Chat feature area coding guidelines.