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/mininglamp-oss/octo-server/agents-mdgit clone --depth 1 https://github.com/Mininglamp-OSS/octo-serverWrote 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/mininglamp-oss/octo-server/agents-md)<a href="https://agentmods.dev/instructions/mininglamp-oss/octo-server/agents-md"><img src="https://agentmods.dev/badge/instructions/mininglamp-oss/octo-server/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 | $0.02429 | $0.02429 |
| Opus 5 | $0.01215 | $0.01215 |
| Sonnet 5 | $0.00486 | $0.00486 |
| Haiku 4.5 | $0.00243 | $0.00243 |
Grade A, and why
octo-server 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.
How it starts
The opening of the file, as written. The whole thing — 241 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 when working in this repository.
Project Overview
Octo-server is the Go backend for DMWork, an enterprise IM platform. It handles business logic on top of WuKongIM for messaging transport.
- Go module:
github.com/Mininglamp-OSS/octo-server - Go version: 1.25
- Shared library:
github.com/Mininglamp-OSS/octo-libfor config, wkhttp, testutil, register, and model packages - Default branch:
main
Common Commands
# Build
docker build -t octo-server .
# Run tests for a module
go test ./modules/group/...
go test ./modules/message/ -run TestSendMsg
# Run all tests
go test ./...
# Lint
golangci-lint run ./...
Architecture
Request Flow
HTTP (Gin/wkhttp) -> Auth Middleware (pkg/auth/) -> Space Middleware -> API Handler -> Service -> DB (MySQL/DBR)
|
v
WuKongIM (gRPC)
Module System
Modules live in modules/. Each module is auto-registered with init() and
register.AddModule().
Standard module layout:
1module.go: registration entry usinginit()andregister.AddModule()api*.go: HTTP handlers implementingregister.APIRouter.Route(r *wkhttp.WKHttp)service.go: business logic, usually with anIServiceinterfacedb*.go: database operations usinggocraft/dbrmodel.go: data models and response structssql/: SQL migrations embedded with//go:embed sql
Key Packages
| Package | Purpose |
|---|---|
pkg/auth/ |
Token parsing, CacheTokenParser, auth middleware |
pkg/errcode/ |
Error code definitions per module, such as group, message, user, and OIDC |
pkg/httperr/ |
ResponseErrorL and ResponseErrorLWithStatus error facades |
pkg/i18n/ |
Localization SDK: code registry, localizer, renderer, language negotiation, and locales/ |
internal/ |
Internal wiring and module imports |
modules/base/event/ |
Async event system |
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.
- 6d ago First seen · 241 lines · 2,429 tokens per session scan A 68bc728bd942
octo-server AGENTS.md is an instructions file published in the GitHub repository Mininglamp-OSS/octo-server (823 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,429 tokens to every session, about $0.0121 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
miro-mcp-server CLAUDE.md
Claude Code instructions for olgasafonova/miro-mcp-server, covering miro mcp server, project, architecture, key patterns and tool categories (110 total).
miro-mcp-server AGENTS.md
AGENTS.md instructions for olgasafonova/miro-mcp-server, covering agent instructions, quick reference, landing the plane (session completion), beads issue tracker and quick reference.
AionUi AGENTS.md
AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
chatgpt-cli CLAUDE.md
Claude Code instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.