WuKongIM is a communication server that stores, synchronizes, and delivers ordered messages between clients over personal, group, or custom channels. It supports messaging applications such as chat, notifications, customer service, live interaction, and IoT communication in single-node or distributed deployments. The catalogue entries provide agents, skills, and instructions for working with the server.
Borrowing it
Nothing to install: this file belongs to WuKongIM/WuKongIM. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/WuKongIM/WuKongIM/main/AGENTS.mdgit clone --depth 1 https://github.com/WuKongIM/WuKongIMWrote 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/wukongim/wukongim/agents-md)<a href="https://agentmods.dev/instructions/wukongim/wukongim/agents-md"><img src="https://agentmods.dev/badge/instructions/wukongim/wukongim/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 | $0.02691 | $0.02691 |
| Opus 5 | $0.01345 | $0.01345 |
| Sonnet 5 | $0.00538 | $0.00538 |
| Haiku 4.5 | $0.00269 | $0.00269 |
Grade A, and why
WuKongIM 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project and Rule Levels
WuKongIM is a high-performance general-purpose messaging system maintained as a Go monorepo.
The keywords MUST, MUST NOT, SHOULD, and MAY define requirement levels:
MUSTandMUST NOTare mandatory.SHOULDis the default unless there is a documented reason to deviate.MAYis optional.
Core Runtime Semantics
- Every deployment is a cluster. A one-node deployment is a single-node cluster, not a standalone mode that bypasses cluster behavior.
- New code MUST NOT add business paths that bypass cluster semantics.
- Documentation, comments, and test names MUST use "single-node cluster" for deployment topology. Use "local" only for behavior within one node.
- Designs MUST account for high-scale workloads such as 100,000-member groups, high message rates, many channels, and many online users.
- Unless explicitly specified otherwise, designs MUST assume 256 hash slots.
Before You Work
- Development SHOULD use a Git worktree with its working copy located in the .worktrees directory
- Before deeply analyzing or changing a package, you MUST read every applicable
FLOW.md. Broad repository discovery and symbol search do not trigger this requirement. A FLOW withscope: packageapplies only to its directory; a FLOW withscope: subtreealso applies to descendants. A FLOW without valid scope metadata is invalid and MUST NOT be used as context. FLOW.mdis advisory module navigation. It MUST NOT override this file, executable code, schemas, or tests. Usedocs/development/FLOW_INDEX.mdonly for discovery; read applicable FLOW files directly before package work.- If a change makes an applicable
FLOW.mdinaccurate, update it in the same change. - More specific
AGENTS.mdfiles in a target subtree add to or override this file for that subtree.
Design and Implementation
Internal Architecture
| Path | Responsibility |
|---|---|
internal/access/* |
Entry-protocol adapters only; no reusable business rules. |
internal/usecase/* |
Entry-agnostic business orchestration. |
internal/runtime/* |
Reusable node-local runtime capabilities; no entry logic. |
internal/infra/* |
Adapters from internal ports to pkg runtimes or external infrastructure. |
internal/app/* |
The only composition root under internal; dependency wiring and lifecycle belong here. |
pkg/gateway/* |
Reusable gateway infrastructure; no product-specific use-case orchestration. |
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 Changed · +12 lines · +124 tokens per session 612fe94712fb
- 6d ago First seen · 221 lines · 2,567 tokens per session scan A e3925b2fd151
WuKongIM AGENTS.md is an instructions file published in the GitHub repository WuKongIM/WuKongIM (4,937 stars, last pushed today), licensed Apache-2.0. It adds 2,691 tokens to every session, about $0.0135 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.