Loushang is an AI work system for carrying complex tasks from an initial intention through execution and verified delivery, with a coding-focused CLI and terminal workbench. It is for software developers who need routed models, persistent sessions, governed tools, and traceable workflows. Catalogue add-ons support its coding workflow.
Borrowing it
Nothing to install: this file belongs to zhnt/loushang. 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/zhnt/loushang/main/AGENTS.mdgit clone --depth 1 https://github.com/zhnt/loushangWrote 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/zhnt/loushang/agents-md)<a href="https://agentmods.dev/instructions/zhnt/loushang/agents-md"><img src="https://agentmods.dev/badge/instructions/zhnt/loushang/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/zhnt/loushang/agents-md"><img src="https://agentmods.dev/badge/instructions/zhnt/loushang/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01876 | $0.01876 |
| Opus 5.5 | $0.00750 | $0.00750 |
| Sonnet 5.5 | $0.00375 | $0.00375 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
loushang 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 11d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository uses a src/ layout. Core package code lives in src/loushang/, with AI-facing modules under src/loushang/ai/, agent code under src/loushang/agent/, and coding/session infrastructure under src/loushang/coding/. Tests live in tests/. Runnable examples live in examples/ai/, with supporting scripts in scripts/ and exploratory work in spikes/. Architecture and design notes belong in docs/.
Worktree Lane Conventions
Use long-lived worktree lanes for major module work:
/home/dev/lsspace/loushangis the control/integration lane. It normally stays onmainand is used for progress management, direction coordination, final verification, merge/push, and small integration-only edits..worktrees/tuiis the long-lived Native TUI lane. For TUI-dominant work, create or switch task branches inside this lane..worktrees/codeis the long-lived V1 code hardening lane. For coding/runtime/session/tool/policy/diagnostics-dominant work, create or switch task branches inside this lane..worktrees/harnessis the long-lived cross-product harness lane. Forloushang.harness, product-neutral shared substrate, coding-to-harness migration, tool/approval/presentation/resource/context boundary work, and harness architecture docs, create or switch task branches inside this lane. Uselane/harnessas an integration branch and keep unfinished harness migration out ofmain; seedocs/internals/architecture/harness/development-workflow.md..worktrees/methodis the long-lived method/work-runtime lane when method-layer work is active. Forloushang.method, method execution semantics, MethodPlan/WorkEvent projection, and work/method integration work, create or switch task branches inside this lane..worktrees/aiis the long-lived AI/provider lane when AI-layer work is active. For AI/provider/model/usage/auth work, create or switch task branches inside this lane..worktrees/agentis the long-lived agent-runtime lane when agent-layer work is active. For agent loop/session orchestration/queue/tool-call semantics work, create or switch task branches inside this lane..worktrees/ontologyis the long-lived ontology lane. Forloushang.ontology, operational ontology infrastructure, semantic schema/runtime, ontology actions/functions, standards interoperability, data fusion, and ontology architecture docs, create or switch task branches inside this lane. Uselane/ontologyas its integration branch and keep it synchronized with the control lane's latestmain.
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.
- 11d ago Changed · +6 lines · +89 tokens per session dca97683ba8b
- 12d ago Changed · +10 lines · +135 tokens per session 57525ff445fd
- 13d ago Changed · +13 lines · +135 tokens per session fc4df4d34267
- 1mo ago Changed · +9 lines · +141 tokens per session d55d0b653d75
- 1mo ago First seen · 57 lines · 1,376 tokens per session scan A 487e300a719e
loushang AGENTS.md is an instructions file published in the GitHub repository zhnt/loushang (1,884 stars, last pushed today), licensed Apache-2.0. It adds 1,876 tokens to every session, about $0.0075 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.