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/agntcms/agntcms/sectionsnpx skills add agntcms/agntcms --skill sectionsgit clone --depth 1 https://github.com/agntcms/agntcmsWhat 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 | $0.00043 | $0.05453 |
| Opus 5 | $0.00022 | $0.02727 |
| Sonnet 5 | $0.00009 | $0.01091 |
| Haiku 4.5 | $0.00004 | $0.00545 |
Grade A, and why
agntcms-sections 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 2d 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 — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agntcms Section Creation
Creating a section is exactly two operations. Both are required. Partial state — a folder without a config entry, or a config entry without a folder — is invalid and will either be invisible to the framework or cause a compile-time import error.
Step 1: Create the section folder
Create agntcms/sections/<SectionName>/ and populate it with the following files.
index.ts (required)
The entry point for the section. Calls defineSection and exports the SectionDefinition.
import { defineSection, TextField, ImageField } from '@agntcms/next'
import { Hero } from './component'
export const HeroSection = defineSection({
name: 'Hero',
category: 'Hero',
schema: { title: TextField, image: ImageField },
component: Hero,
})
The name value ('Hero') is the string that content JSON uses in the type field. It must
be unique across all registered sections. Choose it carefully — renaming it later requires
a migration of all content files that reference the old name.
category is optional but should always be set. It groups sections in the picker modal.
Canonical values used by the template: 'Hero', 'Content', 'CTA', 'Features',
'Social Proof', 'Forms', 'Layout', 'Global'. Any string is valid — these are just the
established conventions. See agntcms-section-new for the full list and guidance.
component.tsx (required)
The React component that renders the section. Props must match the schema exactly — TypeScript
will catch mismatches at compile time. Use EditableText, EditableImage, and other
<EditableX> components from @agntcms/next/client so fields are inline-editable through
the live UI. Since v0.2, Props use EditableSlot<K, V> instead of raw value types — this
means rendering a field as {title} directly in JSX is a compile error. The type system
enforces that every editable field is passed to an <EditableX> wrapper.
For LinkField fields, EditableLink renders only the label text; wrap it in an <a>
element in the section component (the section controls href and target/rel, the editor
controls the label). Use read(slot) from @agntcms/next/client to unwrap the slot to a
bare LinkValue for use with hrefOf(). See agntcms-section-new for the full pattern.
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.
- 2d ago First seen · 470 lines · 43 tokens per session scan A ef66d6c9ed30
agntcms-sections is a skill published in the GitHub repository agntcms/agntcms (19 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 5,453 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 2026-08-30.
Other skills, from other repositories
e2e-write-visual-test
Use when writing a Playwright visual regression (screenshot comparison) test, tagging a test @visual, generating or updating baseline screenshots, running visual tests locally, or debugging a failing screenshot comparison in CI.
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
review-agents-md
Audit Dograh AGENTS.md files for drift against the live repo and for bad scope boundaries between parent and child docs. Use when the user asks to review existing AGENTS files, identify stale guidance, decide whether a subtree needs its own AGENTS.md, or update the AGENTS.md hierarchy under the repo root, api/, or ui/.
clip-hand-skill
Expert knowledge for AI video clipping — yt-dlp downloading, whisper transcription, SRT generation, and ffmpeg processing.
twitter-hand-skill
Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…