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/forgeyclap/claude-forge/forge-cmsnpx skills add ForgeyClap/claude-forge --skill forge-cmsgit clone --depth 1 https://github.com/ForgeyClap/claude-forgeWrote 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/forgeyclap/claude-forge/forge-cms)<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-cms"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-cms.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.01582 |
| Opus 5 | $0.00026 | $0.00791 |
| Sonnet 5 | $0.00010 | $0.00316 |
| Haiku 4.5 | $0.00005 | $0.00158 |
Grade A, and why
forge-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 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge playbook — CMS (WordPress · headless)
A CMS is a content-model + editor-safety + migration domain sitting on top of a live database and uploads. The rendered front-end defers to forge-website (real content, responsive, a11y, SEO, performance); the API/secret/webhook plumbing defers to forge-integration; this file governs the content model, the CMS-specific attack surface, and migration/backup safety. The single most important rule is back up before you change anything — CMS mistakes hit live content and are often irreversible without a backup. Honest limit: Forge cannot run a live WordPress/MySQL install or take a real DB/uploads backup unless the environment provides PHP + MySQL + WP-CLI (opt-in, owner-side) — mark those steps not-run when the runtime is absent.
Hard rules (non-negotiable)
- Content model first. Define post types / fields / taxonomies (WordPress custom post types + ACF/meta) or the headless schema (Contentful/Sanity/Strapi/Payload content types) before templating. Editors must be able to change content without touching code — no business copy hardcoded in the theme.
- No secrets in the theme or repo. DB credentials, salts, API tokens, and SMTP creds live in env /
wp-config.php(via env constants), never committed.wp-config.phpwith real values is never in git; headless API tokens are server-side only. - WordPress output/input safety. Escape on output (
esc_html/esc_attr/esc_url/wp_kses), sanitize on input (sanitize_text_fieldetc.), and use$wpdb->preparefor every query — WP is a large XSS/SQLi surface. Nonces (wp_verify_nonce) + capability checks (current_user_can) on every state-changing action. Never edit WordPress core; extend via a child theme and properly enqueued scripts/styles (wp_enqueue_*). Vet third-party plugins (source, active maintenance, known CVEs) and pin versions. - Headless token + webhook hygiene. Read/write API tokens stay server-side and are never shipped to the browser; preview/draft tokens are scoped and short-lived; CORS is locked to known origins; CMS→build webhooks verify their signature before triggering a rebuild (defer to
forge-integration). - Backup before change; reversible, staged migrations. Take a full DB + uploads backup before any plugin/theme/core update or content migration. Migrations run on staging first and are reversible. Serialized data (WP
wp_options, meta) must be changed with a serialization-safe tool —wp search-replace(WP-CLI), never a raw SQL find/replace, which corrupts serialized PHP and silently breaks the site. - Keep it patched; least privilege. Core, themes, and plugins stay on security-patched versions; user roles follow least privilege (no gratuitous Administrators).
- Performance + accessibility are gates, not extras. Page/object caching, image optimization, minimal plugin bloat, lazy-loading; and a11y on rendered output (semantic markup, alt text, heading order, contrast) — the CMS must emit accessible, fast HTML.
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 · 41 lines · 51 tokens per session scan A 2a23c7dfd396
forge-cms is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,582 once invoked, about $0.0003 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
frame-macos-notification
拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
deck-pitch
10 页融资 deck, 白底 + 蓝紫渐变 hero, traction 柱状, $X.XM ask.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.