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 skills/danielgnh/statamic-mcp/statamic-mcp-setupnpx skills add danielgnh/statamic-mcp --skill statamic-mcp-setupgit clone --depth 1 https://github.com/danielgnh/statamic-mcpWhat 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 | $0.00044 | $0.01126 |
| Opus 5 | $0.00022 | $0.00563 |
| Sonnet 5 | $0.00009 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
statamic-mcp-setup 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Statamic MCP Setup
When to use this skill
Use this skill when the developer wants to connect an AI client (Claude Code, Cursor, claude.ai, Claude Desktop, ChatGPT) to their Statamic site, or when the MCP endpoint answers 401/503 and needs fixing.
Pick the auth mode
- Token mode — clients that can send an
Authorization: Bearerheader: Claude Code, Cursor, MCP Inspector. Works on every install, no database needed. - OAuth mode — connector clients that cannot send static headers: individual-plan claude.ai, Claude Desktop, ChatGPT. Requires Laravel Passport and a database for Passport's own tables (sqlite is fine). Users stay wherever they are — file users work; no user migration.
Always diagnose first
php please mcp:doctor
Every [FAIL] line carries its exact remedy; [WARN]s alone still exit 0. Fix
[FAIL]s via the setup wizard below — not by hand-editing config files.
Token mode
php please mcp:setup --token [email protected] --yes
This issues the first token (shown exactly once) with ready-to-paste client snippets.
More tokens: php please mcp:token [email protected] --name="Claude" --expires-days=90.
The user must have the Access MCP permission (or be super).
OAuth mode
php please mcp:setup --oauth --yes
Unattended, this installs Passport, flips STATAMIC_MCP_AUTH=oauth, runs the
migrations — Passport's tables, the addon's key table, and the conversion of
user_id columns to strings (Statamic ids are UUIDs; Passport's stock columns
are bigint) — and provisions the encryption keys into the database. The migrate
step runs after the env flip on purpose: the addon's migrations only load in
OAuth mode. It finishes by running mcp:doctor and exits non-zero if anything
is still wrong.
There is no user migration, no HasApiTokens trait, and no api guard step: the
addon registers its own auth guard that validates bearers with Passport's
ResourceServer and resolves the user through the Statamic repository —
config/auth.php and the user model are never touched.
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 · 94 lines · 44 tokens per session scan A 919eed60f903
statamic-mcp-setup is a skill published in the GitHub repository danielgnh/statamic-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,126 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
api-connector-builder
Use when writing a client for someone else's REST or GraphQL API: auth flow choice and token refresh, pagination to exhaustion, retry-with-jitter on transient failures only, rate-limit-aware throttling. NOT inbound callbacks (that is webhooks), NOT chaining services (that is automation-flows), NOT designing your own…
alembic-migration
Write an Alembic migration for a new ORM model, column, or index. Covers the SQLite/PG dual-track rules, idempotency helpers, the timezone-aware timestamp trap, dialect branching in data migrations, and when to apply. Use whenever a change adds or alters anything in src/fimone/db/models/.
cut-release
Cut a release before answering "what's next" / "接下来做什么". Archives the changelog's Unreleased section, marks the roadmap version shipped, bumps the version in both places it lives, and verifies the five-way version chain agrees.
user-owned-module
Wire a new user-owned module into user deletion. Use whenever a change adds a table with a FK to users, or writes files under uploads/ or data/ keyed by user, conversation, or any other per-user id. Covers purgeuserdata(), the file cleanup registry, and the FK-cascade trap.
github
通过 GitHub 的 git / REST API 处理仓库操作，尤其是推送 dev、创建和合并从 dev 到 main 的 pull request、等待 GitHub Actions 产出正式 release，以及在 Alice 仓库里执行发布后的自更新。用户提到 GitHub、PR、merge、release、tag、Actions、CI、创建新发行版、更新自己时使用。.
alice-goal
为当前会话设定并持续执行长期目标.