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/zhnt/loushang/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.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 | $0.01376 | $0.01376 |
| Opus 5 | $0.00688 | $0.00688 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00138 | $0.00138 |
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 3d 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 — 57 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.
- 3d 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 (1,291 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,376 tokens to every session, about $0.0069 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
lastlight CLAUDE.md
Instructions for nearform/lastlight, covering last light — monorepo orientation, workspace map, published packages (seven), dependency graph (workspace edges) and logging — use the logger, never console.
tuui AGENTS.md
Instructions for AI-QL/tuui, covering agents guidelines for this repository, 1. use the development server, not npm run build, 2. keep dependencies in sync, 3. coding conventions and 4. project structure.
scaffold AGENTS.md
Instructions for victusfate/scaffold, covering agent guidelines, session start, responsiveness & steerability, answer the user first and surface direction before building.
cetridr AGENTS.md
Instructions for cetridr/cetridr, covering agents.md, project, repo layout (pnpm monorepo), commands and architecture.
momo-code AGENTS.md
AGENTS.md instructions for momozi1996/momo-code, covering agents.md -- project agent instructions, how to work with this codebase, getting started, making changes and quality gates (enforced).
momo-code CLAUDE.md
Claude Code instructions for momozi1996/momo-code, covering claude.md -- agent working agreement, project context, code patterns, testing and commit style.