Borrowing it
Nothing to install: this file belongs to dligthart/wordclaw. 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/dligthart/wordclaw/main/.agents/skills/wordclaw-cms/SKILL.mdgit clone --depth 1 https://github.com/dligthart/wordclawWrote 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/dligthart/wordclaw/wordclaw-cms)<a href="https://agentmods.dev/skills/dligthart/wordclaw/wordclaw-cms"><img src="https://agentmods.dev/badge/skills/dligthart/wordclaw/wordclaw-cms/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/dligthart/wordclaw/wordclaw-cms"><img src="https://agentmods.dev/badge/skills/dligthart/wordclaw/wordclaw-cms.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 | $0.00088 | $0.02412 |
| Opus 5 | $0.00044 | $0.01206 |
| Sonnet 5 | $0.00018 | $0.00482 |
| Haiku 4.5 | $0.00009 | $0.00241 |
Grade A, and why
wordclaw-cms 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 8d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WordClaw CMS Skill
You are connected to a WordClaw content runtime. Do not invent a workflow
when the runtime can tell you what to do. Prefer the built-in discovery
resources, guide_task, and resolve_workspace_target over guessing tool
order from memory.
If the WordClaw MCP resources or tools are not available in the current Codex session, say that clearly and ask for the MCP server to be configured instead of fabricating runtime state.
Session Start
For every new session, or whenever the actor or domain may have changed:
- Read
system://capabilities - Read
system://deployment-status - Read
system://current-actor - Read
system://workspace-contextorsystem://workspace-context/{intent} - If you do not know which task model to use, read
system://agent-guidance - Call
guide_taskfor the current job, orresolve_workspace_targetwhen you need the single best content or work target
If deployment status reports domainCount: 0, call
guide_task("bootstrap-workspace"), then bootstrap the first domain with MCP
create_domain or the REST fallback POST /api/domains before calling any
content write tool.
guide_task supports these live task IDs:
bootstrap-workspacediscover-deploymentdiscover-workspaceauthor-contentreview-workflowmanage-integrationsconsume-paid-contentverify-provenance
Skip discovery only when you are resuming a known operation and the user made it explicit that the cached workspace state is still valid.
Hard Rules
- Never call a write tool before discovery unless you are explicitly resuming a known task.
- Do not assume
AUTH_REQUIRED=falsemeans anonymous writes are allowed. Treat writes as credentialed unless discovery explicitly shows insecure local admin is active. - Prefer
guide_taskover a hand-written plan when a supported task ID exists. - Respect
recommendedNextActionin API and MCP responses. - Dry-run create, update, delete, and batch operations when supported unless the user opts out.
- Respect the active domain from
system://current-actorandsystem://workspace-context. - Never auto-approve a review task without inspecting the content and any review comments.
- Asset bytes and paid content are REST-first, even when discovery happens over MCP.
- If a read returns
PAYMENT_REQUIREDorOFFER_REQUIRED, switch to the REST offer and purchase flow. - If a paid read returns
ENTITLEMENT_AMBIGUOUS, retry withx-entitlement-id. - Prefer
subscribe_eventsrecipe subscriptions over polling when you need to stay attached to live state.
What ships with it
1 file 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.
- 8d ago First seen · 294 lines · 88 tokens per session scan A 79f229eadfb4
wordclaw-cms is a skill published in the GitHub repository dligthart/wordclaw (2 stars, last pushed 5mo ago), licensed MIT. It adds 88 tokens to every session and 2,412 once invoked, about $0.0004 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
payload
Use when working with Payload projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Use when debugging validation errors, security issues, relationship queries, transactions, or hook behavior.
webiny-api-cms-content-models
Creating Headless CMS content models via code using the ModelFactory pattern. Use this skill when the developer wants to create, modify, or understand content model definitions, define fields and validators, set up reference fields between models, configure field layouts (including nested layouts inside object or…
webiny-form-model
Building forms with the FormModel system — field types, renderers, layout, validation, conditional rules, computed fields, and dynamic zones. Use this skill when the developer needs to define form fields with the builder API, choose renderers, build layouts with tabs/rows/separators, add validation (Zod or…
webiny-api-architect
The hub skill for all API/backend architecture in Webiny. Covers architecture overview, Services vs UseCases, feature naming and organization, feature structure templates, DI decision tree, anti-patterns, createFeature, createAbstraction, container registration, domain errors, entity patterns, naming conventions…
webiny-v5-to-v6-migration
Migration patterns for converting v5 Webiny code to v6 architecture. Use this skill when migrating existing v5 plugins to v6 features, converting context plugins to DI services, adapting v5 event subscriptions to v6 EventHandlers, or understanding how v5 patterns translate to v6. Targeted at AI agents performing…
webiny-sdk
Using @webiny/sdk to read and write CMS data from external applications. Use this skill when the developer is building a Next.js, Vue, Node.js, or any external app that needs to fetch or write content to Webiny, set up the SDK, use the Result pattern, list/get/create/update/publish entries, filter and sort queries…