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.
git clone --depth 1 https://github.com/shaharsha/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/plugins/shaharsha/claude-skills/shaharsha-skills)<a href="https://agentmods.dev/plugins/shaharsha/claude-skills/shaharsha-skills"><img src="https://agentmods.dev/badge/plugins/shaharsha/claude-skills/shaharsha-skills/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/plugins/shaharsha/claude-skills/shaharsha-skills"><img src="https://agentmods.dev/badge/plugins/shaharsha/claude-skills/shaharsha-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
shaharsha-skills 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.
What it actually says
{
"name": "shaharsha-skills",
"description": "All 21 agent skills - gdoc-sync, gslides-sync, gsheets, presentation-generator, narrating-pptx, deck-to-video, self-presenting-decks, brand-system, brand-assets, image-generation, prompt-engineer, writing-project-instructions, tech-design-doc, namecheap-domains, office-render, viewing-videos, proton-pass, excalidraw-diagrams, tavily-extract, codex-review, working-with-other-sessions",
"source": "./",
"strict": false,
"skills": [
"./skills/gdoc-sync",
"./skills/gslides-sync",
"./skills/gsheets",
"./skills/presentation-generator",
"./skills/narrating-pptx",
"./skills/deck-to-video",
"./skills/self-presenting-decks",
"./skills/brand-system",
"./skills/brand-assets",
"./skills/image-generation",
"./skills/prompt-engineer",
"./skills/writing-project-instructions",
"./skills/tech-design-doc",
"./skills/namecheap-domains",
"./skills/office-render",
"./skills/viewing-videos",
"./skills/proton-pass",
"./skills/excalidraw-diagrams",
"./skills/tavily-extract",
"./skills/codex-review",
"./skills/working-with-other-sessions"
]
}What it installs
The manifest is a name and a version. 21 skills travel with it, and installing the plugin installs all of them — 3,011 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill presentation-generator A 264 tokens
- Skill brand-system A 132 tokens
- Skill gsheets A 156 tokens
- Skill image-generation A 107 tokens
- Skill narrating-pptx A 121 tokens
- Skill deck-to-video A 0 tokens
- Skill gdoc-sync A 123 tokens
- Skill gslides-sync A 136 tokens
- Skill excalidraw-diagrams A 156 tokens
- Skill tech-design-doc A 113 tokens
- Skill namecheap-domains A 172 tokens
- Skill office-render A 112 tokens
- Skill self-presenting-decks A 98 tokens
- Skill proton-pass A 65 tokens
- Skill prompt-engineer A 320 tokens
- Skill writing-project-instructions A 185 tokens
- Skill brand-assets A 118 tokens
- Skill working-with-other-sessions B 167 tokens
- Skill codex-review B 113 tokens
- Skill tavily-extract B 222 tokens
- Skill viewing-videos C 131 tokens
What ships with it
1 file beside marketplace.json#shaharsha-skills 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 · 29 lines scan A 144f7454e2f8
shaharsha-skills is a plugin published in the GitHub repository shaharsha/claude-skills (5 stars, last pushed 14d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
file-and-image-utilities
Utility skills for local file workflows, NAS file operations, image conversion, and image deduplication or cleanup.
apple-creator-studio-skills
Apple Creator Studio workflows for production and delivery.
canvas
Spawn and control interactive terminal displays (calendars, documents, flights) with real-time IPC communication.
seameet
Operate the SeaMeet desktop recorder from Claude Code: record screen/audio, transcribe meetings, capture bug reports, and turn meetings into action items.
cadence
Focus music for Claude Code. Detects your current work mode and plays Spotify music matched to the task, learning your taste over time.
business-skills
Business productivity skills including business presentation generation.