agent-skills-standard Cursor规则

Quick Start

4. (Optional) Enable runtime enforcement via the MCP server

The CLI distributes skills to disk. The companion MCP server serves them to your AI agent at runtime as explicit tool calls — closing the gap where agents read AGENTS.md but forget to load matched SKILL.md files (especially in sub-agents).

Consent model — you choose the scope

init and sync ask once whether to enable MCP and at what scope. Three choices, recommended in bold:

The CLI never reads or modifies user-home files unless you explicitly choose user scope AND confirm each write. All decisions are recorded in .skillsrc so you're not re-prompted on every sync.

Manage MCP integration with the mcp subcommand

ags mcp status                 # Show enabled, scope, and per-agent install state
ags mcp enable                 # Turn on (uses configured scope)
ags mcp disable                # Turn off (existing entries kept; use uninstall to clean)
ags mcp scope project          # Change scope: project | user | snippets-only | disabled
ags mcp install                # One-shot install at the configured scope
ags mcp uninstall --from=all   # Remove our entry from project + user configs
ags mcp snippets               # Regenerate ./mcp-config-snippets/ without touching configs

Or edit .skillsrc directly:

mcp:
  enabled: true
  scope: project # project | user | snippets-only | disabled
  prompted: true # set to false to be re-asked next sync

Manual install (if you prefer)

Add to your runtime's MCP config:

{
  "mcpServers": {
    "agent-skills-standard": {
      "command": "npx",
      "args": ["-y", "agent-skills-standard-mcp"],
    },
  },
}

Now any sub-agent in any runtime can call load_skills_for_files, audit_session_compliance, etc. Works in Claude Code, Cursor, Antigravity, Kiro, Continue, Gemini CLI — anywhere MCP is supported. Full setup: mcp/README.md.

CLI vs MCP — paired layers, not alternatives

Use both when you want enforcement receipts: the CLI installs the rules, the MCP makes sure agents load them.

---

Configuration

The .skillsrc file controls what gets synced:

```yaml registry: https://github.com/HoangNguyen0403/agent-skills-standard agents: [cursor, copilot, claude, gemini]

What the CLI Does

• Downloads text only — fetches Markdown and JSON from the public registry
• No telemetry — zero data collection, no analytics, no background daemons
• No code or project data leaves your machine — feedback is only sent if you explicitly run ags feedback

Done. Your AI now has portable team standards and SDLC workflows.

```

If ags -V still shows an old version after reinstalling, check your PATH order. ~/Library/pnpm must come before ~/Library/pnpm/bin, then run hash -r and verify with ags -V again.

---

SDLC Workflow Spine

The registry now ships a compact lifecycle that agents can run natively after sync:

Workflow Selection

workflows:
  - sdlc
  - brainstorm-feature
  - plan-feature
  - design-solution
  - implement-feature
  - verify-work
  - pentest
  - security-test
  - deploy-release
  - publish-notes
  - retro-learn

Workflows sync to the native surface for each selected agent. Keep .agents/workflows as the canonical source in this registry; Codex receives generated workflow skills under .codex/skills/<workflow>/SKILL.md.

---

FAQ

<details> <summary><b>Does this work with Cursor, Claude Code, Copilot, Gemini?</b></summary> <br> Yes — all of them, plus Windsurf, Trae, Kiro, Roo, and Antigravity. The CLI generates each agent's native format automatically. No plugin needed. </details>

<details> <summary><b>How is this different from .cursorrules or system prompts?</b></summary> <br> <code>.cursorrules</code> and system prompts are static — one big file that the AI reads every time, wasting context. Agent Skills Standard uses <b>hierarchical on-demand loading</b>: the AI only reads the specific skills relevant to what you're editing right now. This saves ~86% of tokens and scales to 237+ skills without performance loss. </details>

<details> <summary><b>Will it overwrite my custom rules?</b></summary> <br> No. Use <code>custom_overrides</code> in your <code>.skillsrc</code> to protect any files you've customized locally. The CLI will skip them during sync. </details>

<details> <summary><b>How do I add my own skills?</b></summary> <br> Create a <code>SKILL.md</code> file in your agent's skills directory (e.g., <code>.cursor/skills/my-custom/SKILL.md</code>). It will be automatically included in the index on the next sync. For contributing to the public registry, see below. </details>

<details> <summary><b>What about token costs?</b></summary> <br> Each skill averages ~500 tokens (vs ~3,600 for a typical architect prompt). The hierarchical index adds only ~25 lines of scanning overhead per edit. Teams report <b>86% reduction</b> in prompt-related token usage. </details>

---