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/conversejs/converse.js/agents-mdgit clone --depth 1 https://github.com/conversejs/converse.jsWhat 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 | $0.04569 | $0.04569 |
| Opus 5 | $0.02285 | $0.02285 |
| Sonnet 5 | $0.00914 | $0.00914 |
| Haiku 4.5 | $0.00457 | $0.00457 |
Grade A, and why
converse.js 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 2d 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 — 540 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Converse.js Agent Guidelines
Converse.js is an XMPP chat client built with JavaScript and web tech. It has a plugin-based architecture, uses JSDoc TypeScript type definitions, Bootstrap 5 and Lit UI components.
Project Overview
- Type: XMPP/Jabber web-based chat client
- Build Tool: Rspack (Webpack-compatible)
- UI Framework: Lit (Web Components)
- Testing: Vitest (browser mode, Playwright/Chromium) with a Jasmine-compat shim
- Styling: SCSS with Bootstrap 5
- Language: JavaScript
- Type System: TypeScript via JSDoc annotations
Monorepo
Three npm workspaces:
-
Root (
/): Main package with UI plugins (src/plugins/) -
Headless (
src/headless/): Core XMPP logic and state management, separate package@converse/headlessThe@converse/headlesspackage resolves to the built bundle (dist/converse-headless.js), not to individual source files. Importing from relative paths pointing tosrc/headless/back into the main package likesrc/pluginsis forbidden since they cross the package boundary.Read: src/headless/AGENTS.md
-
Log (
src/log/): Logging utility, separate package@converse/log
Key Entry Points
src/index.js— Main entrysrc/headless/index.js— Headless entryrspack/— Build configs
Directory Structure
src/
├── headless/ # Core XMPP logic (separate package @converse/headless)
│ ├── plugins/ # Headless plugins (chat, muc, roster, etc.)
│ ├── shared/ # Shared headless utilities
│ ├── types/ # Generated TypeScript definitions
│ └── dist/ # Built headless package
├── plugins/ # UI plugins
│ ├── chatview/ # Chat UI
│ ├── muc-views/ # Multi-user chat UI
│ ├── rosterview/ # Contact list UI
│ └── controlbox/ # Main control panel
├── shared/ # Shared UI components
│ ├── components/ # Reusable Lit components
│ ├── chat/ # Chat-related shared components
│ ├── modals/ # Modal dialogs
│ └── styles/ # Shared SCSS files
├── templates/ # Lit template functions
├── i18n/ # Internationalization
│ └── locales/ # Translation files (.po)
├── types/ # Generated TypeScript definitions
└── utils/ # Utility functions
media/ # Sponsor logos (separate repo: conversejs/media)
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.
- 2d ago First seen · 540 lines · 4,569 tokens per session scan A d206d85b0c27
converse.js AGENTS.md is an instructions file published in the GitHub repository conversejs/converse.js (3,291 stars, last pushed 16d ago), licensed MPL-2.0. It adds 4,569 tokens to every session, about $0.0228 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
AionUi AGENTS.md
AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
obot CLAUDE.md
Instructions for obot-platform/obot, covering claude.md, project overview, tech stack, common commands and development.
octo-server AGENTS.md
Instructions for Mininglamp-OSS/octo-server, covering agents.md, project overview, common commands, build and run tests for a module.
vscode-unify-chat-provider AGENTS.md
Instructions for smallmain/vscode-unify-chat-provider, a project described as: Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat using the Language Model API. One-click use of your Claude Code, Gemini CLI, Antigravity, Github Copilot, OpenAI Codex (ChatGPT Plus/Pro), xAI Grok (SuperGrok / X…
openbridge-webcomponents watch-radial-instruments.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering watch & radial instruments, architecture overview, key principle: logic in watch.ts, instruments stay thin, shared sibling modules and layering & stacking pattern.
technocore-chat AGENTS.md
Instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.