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 jamdesk/jamdesk-claude-plugin --skill jamdeskgit clone --depth 1 https://github.com/jamdesk/jamdesk-claude-pluginWrote 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/jamdesk/jamdesk-claude-plugin/jamdesk)<a href="https://agentmods.dev/skills/jamdesk/jamdesk-claude-plugin/jamdesk"><img src="https://agentmods.dev/badge/skills/jamdesk/jamdesk-claude-plugin/jamdesk/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/jamdesk/jamdesk-claude-plugin/jamdesk"><img src="https://agentmods.dev/badge/skills/jamdesk/jamdesk-claude-plugin/jamdesk.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 | $0.00057 | $0.03525 |
| Opus 5.5 | $0.00023 | $0.01410 |
| Sonnet 5.5 | $0.00011 | $0.00705 |
| Haiku 4.5 | $0.00006 | $0.00352 |
Grade A, and why
jamdesk 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 yesterday.
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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference Files
Read these only when your task requires them — the quick reference below covers most needs:
| File | When to read |
|---|---|
reference/components.md |
Adding or modifying MDX components (Cards, Steps, Tabs, Callouts, etc.) — full props and examples |
reference/configuration.md |
Changing docs.json settings (theme, colors, navbar, footer, integrations) — complete schema |
reference/navigation.md |
Modifying site navigation (tabs, groups, products, versions, languages) — 8 patterns |
Before You Start
- Read the project's
docs.jsonto understand current configuration - Search existing pages before creating new ones — avoid duplicates
- Read 2-3 similar pages to match the project's voice and conventions
- Run
jamdesk validatebefore deploying to catch config errors
Project Structure
my-docs/
├── docs.json # Configuration (required)
├── introduction.mdx # Pages (at least one required)
├── guides/
│ ├── quickstart.mdx
│ └── advanced.mdx
├── api/
│ ├── overview.mdx
│ └── openapi.yaml # OpenAPI spec (optional)
├── images/
│ ├── logo.webp
│ └── favicon.png
└── snippets/ # Reusable MDX fragments
└── install-tabs.mdx
Page Frontmatter
---
title: Page Title # Required — used as H1 and browser tab title
description: SEO summary # Recommended — meta description for search engines
sidebarTitle: Short Name # Optional — override the sidebar label
icon: rocket # Optional — Font Awesome icon in sidebar
---
All frontmatter fields:
| Field | Type | Description |
|---|---|---|
title |
string | Page title (required) |
description |
string | Meta description for SEO |
sidebarTitle |
string | Override sidebar label |
icon |
string | Font Awesome icon name |
mode |
string | Layout: default, wide, custom, frame, center |
openapi |
string | OpenAPI operation (e.g., GET /users) |
asyncapi |
string | AsyncAPI operation — accepted but not rendered; nothing is generated from it |
keywords |
string[] | SEO keywords for search indexing |
noindex |
boolean | Exclude page from search engines and sitemap |
search |
boolean | false keeps the page out of site search, AI chat, and MCP, while leaving it in navigation, the sitemap, and llms.txt (not the same as hidden) |
tag |
string | Badge label in sidebar (e.g., "New", "Beta") |
lastUpdatedDate |
string | Override the "Last updated on" date (must be quoted, e.g. "2026-09-22") — otherwise derived from the last git commit to the file |
What ships with it
3 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.
- yesterday Changed · +4 lines c747c9fd1564
- 5d ago Changed · +35 lines 84824970cece
- 1mo ago Changed · +1 lines 2b1a0f7c022b
- 1mo ago First seen · 277 lines · 57 tokens per session scan A e1467d2ce2ec
jamdesk is a skill published in the GitHub repository jamdesk/jamdesk-claude-plugin (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 3,525 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
unslop
Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse, "delve"/"tapestry"/"testament", hedging stacks, tidy five-paragraph shapes), engineers burstiness and calibrated uncertainty, and preserves technical accuracy. Supports intensity levels: subtle…
unslop-file
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly. Two modes: --deterministic (fast, regex-based, no API) and LLM (default, calls Claude for rewrite). Humanized version…
unslop-commit
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why"…
unslop-help
Quick-reference card for unslop modes, sub-skills, and slash commands. One-shot display, not a persistent mode. Trigger: /unslop-help, "unslop help", "what unslop commands", "how do I use unslop".
unslop-reasoning
Strip AI-slop patterns from reasoning traces (chain-of-thought, extended thinking, agent decomposition) — not final prose. Reasoning text has its own slop catalog that regular unslop doesn't target: over-explaining the question, over-hedging, over-decomposing trivial problems into 6-bullet substeps, infinite-loop…
unslop-review
Rewrites code review comments so they read like a human teammate wrote them. Cuts corporate-AI throat-clearing ("I noticed...", "I was wondering if perhaps...", "It might be worth considering..."). Each comment is direct: location, the issue, a concrete fix. Use when user says "humanize review", "de-slop PR comment"…