Borrowing it
Nothing to install: this file belongs to huaweicloud/huaweicloud-devkit. 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/huaweicloud/huaweicloud-devkit/main/AGENTS.mdgit clone --depth 1 https://github.com/huaweicloud/huaweicloud-devkitWrote 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/huaweicloud/huaweicloud-devkit/agents-md)<a href="https://agentmods.dev/instructions/huaweicloud/huaweicloud-devkit/agents-md"><img src="https://agentmods.dev/badge/instructions/huaweicloud/huaweicloud-devkit/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/huaweicloud/huaweicloud-devkit/agents-md"><img src="https://agentmods.dev/badge/instructions/huaweicloud/huaweicloud-devkit/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 | $0.02964 | $0.02964 |
| Opus 5.5 | $0.01186 | $0.01186 |
| Sonnet 5.5 | $0.00593 | $0.00593 |
| Haiku 4.5 | $0.00296 | $0.00296 |
Grade A, and why
huaweicloud-devkit 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — HuaweiCloud DevKit
Commands
npm test # all tests (node --test)
npm run lint # ESLint + markdownlint
npm run lint:js # ESLint only
npm run lint:md # markdownlint only
npm run format # Prettier format all files
npm run format:check # Prettier check (no write)
npm run validate # structural validation + README beta badge sync check
npm run badge:sync # rewrite README beta badge to the next stable version
node --test test/structure.test.mjs # single test file
node ./scripts/validate-package.mjs # validation alone
No build step, no typecheck. One runtime dependency (undici for proxy support).
Architecture
This is an agent guidance + safety package, not a service encyclopedia. Six compact meta-skills route agent intent to the right capability path (Skills / KooCLI / API / SDK / MCP / Terraform).
plugins/huaweicloud-core/
skills/ ← 6 meta-skills + service skills
src/ ← Node.js MCP server (stdio/remote JSON-RPC, 43 tools in tools.mjs)
safety/ ← shared policy.json + risk rules
hooks/ ← PreToolUse hook (Node huaweicloud-safety.mjs, wired via hooks.json; .py variant kept for compatibility)
.codex-plugin/ ← Codex plugin manifest
.claude-plugin/ ← Claude Code plugin manifest
.cursor-plugin/ ← Cursor plugin manifest
.workbuddy-plugin/← WorkBuddy plugin manifest
.hermes-plugin/ ← Hermes plugin manifest
.mcp.json ← MCP server config for agents
openclaw.plugin.json ← OpenClaw plugin manifest
Safety is 3-layer: skills teach → hooks block → MCP/CLI wrappers enforce.
Also in the repo:
bin/setup.cjs— interactive installer (huaweicloud-devkit); dispatches to each agent's plugin dir.integrations/— per-agent adapter configs (opencode, dsh, hermes, workbuddy, atomcode), separate from the plugin.src/tools.mjs— 39 MCP tool definitions (hcloud CLI, hooks, catalog, auth, sandbox, voucher, update).src/mcp-server-remote.mjs— remote (HTTP) transport alongside stdio.src/setup-cli.mjs— KooCLI install/doctor logic; honorsHCLOUD_BIN.scripts/*.mjs— validation, version sync, packaging, release helpers..superpowers/+docs/superpowers/— planning/spec workflow used for larger changes.
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 Changed 0382f48688f4
- 1mo ago Changed · +24 lines · +640 tokens per session 1beb2d1d4b81
- 1mo ago Changed · +1 lines · +23 tokens per session b4079a9b4818
- 1mo ago Changed · +1 lines · +127 tokens per session 3c02557a42c6
- 1mo ago First seen · 141 lines · 2,174 tokens per session scan A b8ef8d2d1170
huaweicloud-devkit AGENTS.md is an instructions file published in the GitHub repository huaweicloud/huaweicloud-devkit (69 stars, last pushed today), licensed Apache-2.0. It adds 2,964 tokens to every session, about $0.0119 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
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).