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/lamost423/dsh-maze/agents-mdgit clone --depth 1 https://github.com/lamost423/dsh-mazeWrote 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/lamost423/dsh-maze/agents-md)<a href="https://agentmods.dev/instructions/lamost423/dsh-maze/agents-md"><img src="https://agentmods.dev/badge/instructions/lamost423/dsh-maze/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 | $0.00469 | $0.00469 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
dsh-maze 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.
What it actually says
AGENTS.md
Single-package DSH client plugin. Read README.md for what it does.
src/index.tsis the no-op Host half; the real plugin is the browser bundle fromsrc/client/, wired throughpackage.json'sdsh.clientand inserted bycordis.patch.yml.src/client/maze-upload.htmlis a self-contained page (inline CSS/JS, no imports) rendered via<iframe srcDoc>. Parsing, idle-gap folding, layout, and playback all live in its inline script;tsdown.config.tsinlines it as a string and splices the fzstd UMD build into its/*__FZSTD_UMD__*/placeholder at bundle time.src/client/live-data.tsconverts the liveConversationSnapshotinto the same maze payload the page renders; verdicts settle only from arrived tool results (tests intests/live-data.test.ts).- Verify with
pnpm check(typecheck + vitest + build). Peers pin to the published@deepseek-ai/dsh-*@0.1.0-rc.xline, not to a harness checkout.
Releasing
npm is the primary distribution channel — a GitHub release without a matching npm publish means every npm install silently serves the old version. Both channels must move together.
pnpm release:status— comparespackage.json, the npmlatesttag, and the newest GitHub release. Exits non-zero when they disagree. Run it after every release.pnpm release:prep— guards (clean tree, version not already on npm, npm login still valid), then runspnpm check, packs, verifies the tarball, and prints the two commands left to run.- The final
npm publishandgh release createare manual: npm forces two-factor auth on publish and redacts the auth URL's credential from both stdout and its debug log, so an agent cannot complete it. - Pass the tarball as
./artifacts/<name>.tgz. Without the leading./, npm reads it as a git shorthand and triesssh://[email protected]/artifacts/..., which fails.
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 First seen · 18 lines · 469 tokens per session scan A 3d6de3c147e9
dsh-maze AGENTS.md is an instructions file published in the GitHub repository lamost423/dsh-maze (64 stars, last pushed yesterday), licensed MIT. It adds 469 tokens to every session, about $0.0023 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
DSH-better-sidebar AGENTS.md
AGENTS.md instructions for omdsh-dev/DSH-better-sidebar, covering dsh-better-sidebar 仓库规则（agents）, 1. 仓库硬约束（必须遵守）, 2. ci 挂载冒烟（plugin-mount job / pnpm test:mount）, 3. dsh 0.1.2 适配要点（0.1.2-rc.1+ 基线） and 4. npm 发版（github release → npm publish）.
awesome-dsh-plugin AGENTS.md
Instructions for beancookie/awesome-dsh-plugin, covering agents.md, 内容来源（source of truth）, 目录结构（每个文件夹的作用）, 添加插件 and 整理流程（分类与数量）.
dsh-config-manager AGENTS.md
Instructions for xiajiajun516/dsh-config-manager, covering agents.md — dsh config manager 仓库协作指南, 🗣️ 语言与交流, 📦 项目概览, 🗂️ 仓库结构与职责 and ui 分层（改动前必读，避免放错层）.
causal-memory CLAUDE.md
Claude Code instructions for JingxuanC/causal-memory, covering causal memory mcp integration, causal memory integration, after acting on a decision and observing the result, when something fails unexpectedly and when a recorded lesson turns out to be wrong.
dsh-industry-research AGENTS.md
AGENTS.md instructions for PerryLink/dsh-industry-research, covering agents.md, layout, hard rules applied here, checks and release.
star-dsh-desktop AGENTS.md
AGENTS.md instructions for dabaicai001/star-dsh-desktop, covering agents.md — starhub 协作指引, 项目是什么, 架构一句话, 目录结构 and 技术栈速查.