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 michtio/craftcms-claude-skills --skill servdgit clone --depth 1 https://github.com/michtio/craftcms-claude-skillsWrote 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/michtio/craftcms-claude-skills/servd)<a href="https://agentmods.dev/skills/michtio/craftcms-claude-skills/servd"><img src="https://agentmods.dev/badge/skills/michtio/craftcms-claude-skills/servd/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/michtio/craftcms-claude-skills/servd"><img src="https://agentmods.dev/badge/skills/michtio/craftcms-claude-skills/servd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 21 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00347 | $0.02878 |
| Opus 5 | $0.00173 | $0.01439 |
| Sonnet 5 | $0.00069 | $0.00576 |
| Haiku 4.5 | $0.00035 | $0.00288 |
Grade A, and why
servd 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 12d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Servd — Managed Hosting for Craft CMS
Reference for Servd (servd.host), a Craft-specialised managed hosting platform. Covers git push-to-deploy and the servd.yaml build config, the local → staging → production workflow, the servd/craft-asset-storage plugin, Servd's static caching (and running Blitz alongside it), databases over SSH, backups, the queue runner, the ephemeral filesystem, and how Servd differs from Craft Cloud.
This skill is scoped to Servd specifically — what's different on Servd vs running Craft yourself on Forge or bare metal, and vs Pixel & Tonic's Craft Cloud. For generic Craft deployment, see the craftcms skill's deployment.md. For Craft Cloud, see the craft-cloud skill.
Companion Skills — Load When Needed
craftcms— When the Servd topic intersects plugin or module PHP (ephemeral-filesystem guards, queue-job design, asset filesystem code).craft-site— When Servd intersects front-end templating ({% dynamicInclude %}islands in cached pages, transform usage, CSRF in cached forms).ddev— For local development; Servd has no first-party local environment, so DDEV is the standard local stack.craft-php-guidelines— When editing plugin PHP to add ephemeral-filesystem checks.
Documentation
Authoritative sources used to write this skill (Servd's own docs):
- Docs landing: https://servd.host/docs
- The Servd workflow: https://servd.host/docs/the-servd-workflow
- Node build step (servd.yaml): https://servd.host/docs/node-build-step
- Asset volumes & filesystems: https://servd.host/docs/servd-asset-volumes-and-filesystems
- Installing the plugin: https://servd.host/docs/installing-the-servd-plugin
- Static caching: https://servd.host/docs/static-caching
- Caching with Blitz: https://servd.host/docs/caching-with-blitz
- Handling runtime-created files: https://servd.host/docs/handling-runtime-created-files
- Dedicated queue runner: https://servd.host/docs/dedicated-queue-runner
- Backup & restore: https://servd.host/docs/backup-restore
- Plugin console commands: https://servd.host/docs/servd-plugin-console-commands
- Plugin source: https://github.com/servdhost/craft-asset-storage
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 118 lines · 347 tokens per session scan A 973c9cbc9146
servd is a skill published in the GitHub repository michtio/craftcms-claude-skills (78 stars, last pushed 9d ago), licensed MIT. It adds 347 tokens to every session and 2,878 once invoked, about $0.0017 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 skills, from other repositories
deploy
This skill activates automatically when the task involves.
deploy-site
Deploys an existing Power Pages code site to a Power Pages environment using PAC CLI. Handles tooling verification, authentication, environment confirmation, building, and uploading. Use when the user wants to deploy, upload, or publish their code site.
activate-site
Activates and provisions a Power Pages website in a Power Platform environment via the Power Platform REST API. Use when the user wants to activate, provision, turn on, or enable a Power Pages website or portal.
deploy
Builds and deploys a Power Apps code app to Power Platform. Use when deploying changes, redeploying an existing app, or pushing updates.
skill-monitor
Analyze skill effectiveness across sessions. Computes per-skill metrics (action rate, friction, outcomes), identifies degrading skills, and generates improvement recommendations. Requires session-scan data in metrics.jsonl.
deploy-to-connect
Deploy or publish Python and R content to a Posit Connect server using rsconnect-python or the R rsconnect package. Handles interactive apps and dashboards, web APIs, rendered documents, and prepared bundles/manifests. Use whenever the user asks to deploy, publish, or redeploy content to Posit Connect, or mentions…