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/risa-labs-inc/bossconsole/agents-mdgit clone --depth 1 https://github.com/risa-labs-inc/BossConsoleWrote 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/risa-labs-inc/bossconsole/agents-md)<a href="https://agentmods.dev/instructions/risa-labs-inc/bossconsole/agents-md"><img src="https://agentmods.dev/badge/instructions/risa-labs-inc/bossconsole/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 5.1 | $0.15177 | $0.15177 |
| Opus 5 | $0.07588 | $0.07588 |
| Sonnet 5 | $0.03035 | $0.03035 |
| Haiku 4.5 | $0.01518 | $0.01518 |
Grade A, and why
BossConsole 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 today.
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 — 982 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents working with this repository.
Project Overview
BOSS (Business Operating System Service) is a desktop application built with Kotlin Multiplatform and Compose Multiplatform. It features WebAuthn/passkey authentication, integrated browser (JxBrowser), terminal integration (BossTerm), customizable keyboard shortcuts, and role-based access control.
Target Platforms: Desktop only (macOS, Windows, Linux).
Essential Commands
./gradlew run # Run desktop application
./gradlew showVersion # Display current version
./gradlew test # Run tests
./gradlew build # Build application
./gradlew packageDmg # Build macOS DMG
./gradlew packageMsi # Build Windows MSI
./gradlew packageDistributionForCurrentOS # Linux packages
./gradlew incrementVersion # Increment patch version
Workflow Rules
IMPORTANT: Do NOT run ./gradlew run in a blocking/foreground way just to test - the user runs and tests the app themselves. Exception: launching the app in a dedicated bottom split pane is allowed (backgrounded so it doesn't wedge the pane).
Running commands in a visible terminal pane
When a terminal MCP server is available, prefer it over the plain Bash tool for commands worth showing - it runs in a visible BossTerm pane and still returns stdout/stderr/exit code. Two servers may be present depending on which app hosts the session; use whichever the session's SessionStart hook designates:
mcp__boss__*- exposed by theterminal-tabplugin inside BossConsole (e.g.mcp__boss__run_command,run_in_sidebar).mcp__bossterm__*- exposed by the standalone BossTerm app.
For a bottom split use panel: horizontal_split. Reuse a pane across calls by passing back its pane_id. Keep plain Bash for trivial read-only commands where opening a visible pane is churn. (Do not mix the two servers in one session - they target different app instances.)
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.
- today Changed · +46 lines · +852 tokens per session 9deb5ba8ab66
- 6d ago First seen · 936 lines · 14,325 tokens per session scan A c043dcf65488
BossConsole AGENTS.md is an instructions file published in the GitHub repository risa-labs-inc/BossConsole (427 stars, last pushed today), licensed Apache-2.0. It adds 15,177 tokens to every session, about $0.0759 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
browser-agent AGENTS.md
Instructions for uiuing/browser-agent, covering agents.md — guide for ai coding agents, setup & commands, tests — run these before claiming done, repository layout and architecture invariants (do not break these).
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
nulnul-harness AGENTS.md
AGENTS.md instructions for SeoNaRu/nulnul-harness: This repository builds plugins/nulnul-harness/, a Codex plugin that selects the strongest justified project-local capability system for the requested outcome, verifies the user's work, removes non-contributing setup, and evolves from measured outcomes without…
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
pixir CLAUDE.md
Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.