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 skills add danielgnh/statamic-mcp --skill statamic-mcp-guidelinesgit clone --depth 1 https://github.com/danielgnh/statamic-mcpWrote 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/skills/danielgnh/statamic-mcp/statamic-mcp-guidelines)<a href="https://agentmods.dev/skills/danielgnh/statamic-mcp/statamic-mcp-guidelines"><img src="https://agentmods.dev/badge/skills/danielgnh/statamic-mcp/statamic-mcp-guidelines/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/skills/danielgnh/statamic-mcp/statamic-mcp-guidelines"><img src="https://agentmods.dev/badge/skills/danielgnh/statamic-mcp/statamic-mcp-guidelines.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 | $0.00067 | $0.01308 |
| Opus 5.5 | $0.00027 | $0.00523 |
| Sonnet 5.5 | $0.00013 | $0.00262 |
| Haiku 4.5 | $0.00007 | $0.00131 |
Grade A, and why
statamic-mcp-guidelines 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Statamic MCP Guidelines
When to use this skill
Use this skill when the developer wants agents working through MCP to follow the
site's conventions: which blocks go where, how a page is structured, the site's
voice. Also use it when php please mcp:guidelines lists blocks without
instructions.
Where each kind of guidance lives
Agents get everything through statamic_overview and blueprints_get, so
guidance goes where those tools read it. Each rule lives in exactly one place:
| Guidance | Where it goes | Who edits it |
|---|---|---|
| What one field holds, its format and limits | the field's instructions in the blueprint or fieldset |
the Control Panel's blueprint editor, or the YAML |
| When to use a block and where it goes on a page | the set's instructions |
the same |
| How one blueprint's entry is put together, which entry to follow | the instructions of the blueprint's first section |
the same |
| How a collection's entries are put together, page shapes, block order | a row on Tools → MCP → Guidelines | super admins in the Control Panel, or the YAML in resources/addons/statamic-mcp.yaml |
| Voice and tone for the whole site | the Site field on Tools → MCP → Guidelines | the same |
Never restate a field, set, or section on the Guidelines page.
blueprints_get already returns their instructions, and a copy goes stale the
first time the blueprint changes. Agents can't edit the page through MCP.
Start with the command
php please mcp:guidelines
It prints where the guidelines are written, then lists the blocks that have
no instructions, grouped under the blueprints that share them, one line per
field with the names of its sets. On a site coming from 0.6.0, it first moves
the old guidelines global set to the Guidelines page and deletes it.
Write block instructions
For each block the command lists:
- Find where the set is defined. Search
resources/fieldsets/andresources/blueprints/for the set handle under asets:key. Page builders are usually a fieldset imported into several blueprints, so edit the fieldset. - Find the block's template to learn what it renders. Page builders usually
render each set from a partial named after its handle, for example
resources/views/page_builder/_hero.antlers.htmlor a Blade view. Search the views for the handle. - Add
instructions:to the set, next todisplay:. Write one or two sentences: when to use the block, where it goes on a page, what it should not sit next to. Editors see this text in the Control Panel too, so write it for people as well. - Put a rule about a single field in that field's
instructions, not the set's.
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 · 110 lines · 67 tokens per session scan A 1c30fa976eb2
statamic-mcp-guidelines is a skill published in the GitHub repository danielgnh/statamic-mcp (4 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 1,308 once invoked, about $0.0003 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 2026-09-25.
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…
linkedin-api
Use when wiring an app to LinkedIn's organic Posts / Community Management API — 3-legged OAuth, publishing text, article or document posts to a member profile or company page, and pulling impressions, engagement and follower stats into a durable feedback record. NOT writing the post copy (that is linkedin-content)…
figranium-browser-automation
Build, run, validate, and schedule browser automations with Figranium. Use for rendered websites, repeatable browser workflows, extraction, downloads, forms, and tasks that need real browser interaction.
alice-goal
A session-goal tool that keeps a long-running task active across repeated work sessions. It can create, inspect, pause, resume, delay, or clear a goal.
alice-scheduler
A session scheduler that runs prompts automatically at set intervals or at times described by cron, a standard scheduling format. Each run starts as a separate LLM session.
alice-message
A skill for sending image and file attachments to the current session. It can use either a local file path or an existing Feishu attachment key.