agentmods.dev

bosun AGENTS.md

bosun AGENTS.md is an instructions file for Codex, OpenCode from virtengine/bosun. It costs 857 tokens per session, scanned A, original, Apache-2.0.

A project guide for Bosun, an agent system. It points developers to the right modules and local instruction files for areas such as workflows, tasks, workspaces, servers, and shell executors.

In plain words
What is it for?
Use it to identify where a feature belongs, edit the relevant module, and follow the suggested testing and build commands.
Why use it?
It reduces the time spent locating the correct code and project rules before making a change.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex; mentions OpenCode.

not rated 280 +1 3mo ago A scan 857 tokens original Apache-2.0
View the source file virtengine/bosun bosun.engineer
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/virtengine/bosun/agents-md
Clone the repo
git clone --depth 1 https://github.com/virtengine/bosun

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 bosun AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/virtengine/bosun/agents-md.svg)](https://agentmods.dev/instructions/virtengine/bosun/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/virtengine/bosun/agents-md"><img src="https://agentmods.dev/badge/instructions/virtengine/bosun/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 857 This file is loaded in full into every session.
When invoked 857 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 $0.00857 $0.00857
Opus 5 $0.00428 $0.00428
Sonnet 5 $0.00171 $0.00171
Haiku 4.5 $0.00086 $0.00086

Measured 6d ago against content hash d04dcfe01a6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

bosun 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bosun Agent Guide

Scope

Use this file as the top-level router for work inside bosun/. Open the closest module AGENTS.md before editing.

Start Fast

  1. Confirm task area.
  2. Jump to the mapped module below.
  3. Edit only that module plus directly impacted callers/tests.
  4. Run targeted tests, then npm test, then npm run build.

Core Entry Points

  • CLI: cli.mjs
  • Setup: setup.mjs
  • Monitor loop: infra/monitor.mjs
  • Config loader: config/config.mjs

Module Index

  • agent/AGENTS.md - agent pool, prompts, hooks, autofix, fleet coordination.
  • infra/AGENTS.md - monitor loop, health/recovery, runtime plumbing.
  • workflow/AGENTS.md - workflow engine, nodes, adapters.
  • workflow-templates/AGENTS.md - template library used by workflow engine.
  • task/AGENTS.md - task execution, claims, context, archiving.
  • workspace/AGENTS.md - workspace/worktree/shared-state lifecycle.
  • kanban/AGENTS.md - Kanban adapter layer (GitHub, Jira, internal).
  • server/AGENTS.md - HTTP API and setup/UI servers.
  • telegram/AGENTS.md - Telegram/WhatsApp channels and sentinel.
  • shell/AGENTS.md - executor shells (Codex, Copilot, Claude, OpenCode).
  • github/AGENTS.md - GitHub App/OAuth auth and webhook paths.
  • ui/AGENTS.md - Mini App frontend assets.
  • site/AGENTS.md - marketing/docs website assets.
  • desktop/AGENTS.md - Electron desktop shell.
  • tests/AGENTS.md - test routing and coverage map.
  • config/AGENTS.md - config schema, resolution, repo-root handling.
  • tools/AGENTS.md - build/test utility scripts and maintenance helpers.
  • scripts/AGENTS.md - migration and one-off utility scripts.
  • lib/AGENTS.md - shared lightweight helpers.
  • git/AGENTS.md - git safety, commit helpers, conflict utilities.
  • voice/AGENTS.md - voice relay/auth/tooling modules.
  • _docs/AGENTS.md - long-form source docs for generated docs site.
  • bench/AGENTS.md - SWE-bench benchmarking tooling.
  • bin/AGENTS.md - executable wrappers (git shim).

Common Commands

  • Install: npm install
  • Test: npm test
  • Build: npm run build
  • Syntax check: npm run syntax:check

Read the full file on GitHub · 90 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 · 90 lines · 857 tokens per session scan A d04dcfe01a6c

Subscribe to this mod's changes

bosun AGENTS.md is an instructions file published in the GitHub repository virtengine/bosun (280 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 857 tokens to every session, about $0.0043 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.

Building agentsagentsautomationchatgptclaudeclaude-codecodex
Related

Other instructions, from other repositories

langgraph AGENTS.md

AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.

langchain-ai/langgraph · 477 tokens

langroid CLAUDE.md

Claude Code instructions for langroid/langroid, covering claude.md, commands, development, testing and linting and type checking.

langroid/langroid · 2,637 tokens

langgraph CLAUDE.md

Claude Code instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.

langchain-ai/langgraph · 471 tokens

Proma AGENTS.md

AGENTS.md instructions for proma-ai/Proma, covering proma 工程约定, 必须遵守, 常用命令, 开发 and 构建 / 类型检查 / 测试.

proma-ai/Proma · 1,099 tokens

autogen copilot-instructions.md

Copilot instructions for microsoft/autogen, covering autogen multi-agent ai framework, working effectively, prerequisites and environment setup, python development workflow and quick validation (under 1 second each).

microsoft/autogen · 2,174 tokens

mem9 AGENTS.md

AGENTS.md instructions for unvulcanised-watercress762/mem9, covering what this repo is, high-level modules, commands, go server build / verify and single go test.

unvulcanised-watercress762/mem9 · 1,827 tokens