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.
/plugin marketplace add mpuig/agent-slidesnpx agentmods add plugins/mpuig/agent-slides/marketplacegit clone --depth 1 https://github.com/mpuig/agent-slidesGrade A, and why
agent-slides 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.
What it actually says
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "agent-slides",
"metadata": {
"description": "Agent skill for professional PowerPoint decks. 7 composable skills and a purpose-built CLI to extract templates, build from prompts, audit, critique, and polish presentations."
},
"owner": {
"name": "Marc Puig",
"email": "[email protected]"
},
"plugins": [
{
"name": "agent-slides",
"description": "Agent skill for generating professional PowerPoint decks. 7 composable skills (extract, build, edit, audit, critique, polish, full) powered by a purpose-built CLI and Python API.",
"version": "0.1.0",
"author": {
"name": "Marc Puig",
"email": "[email protected]"
},
"source": "./",
"category": "productivity",
"homepage": "https://agent-slides.com",
"tags": ["slides", "powerpoint", "pptx", "presentations", "agent", "skills"]
}
]
}
What ships with it
1 file beside marketplace.json 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.
- 2d ago First seen · 27 lines scan A bf56c47cf8fc
agent-slides is a plugin published in the GitHub repository mpuig/agent-slides (10 stars, last pushed 5mo 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 2026-08-31.
Other plugins, from other repositories
sd0xdev-marketplace
Plugin marketplace listing 1 plugin: sd0x-dev-flow.
sd0x-harness
Harness engineering for Claude Code — reminder-layer review hooks, behaviour-layer gates, and fail-closed safety where it counts.
auto-harness-marketplace
Plugin marketplace listing 1 plugin: auto-harness.
auto-harness
Run Claude Code like a specialist software team: planning, implementation, QA, fix/retest loops, and durable serial or parallel harness state for long-running project delivery.
forge
Plugin marketplace listing 1 plugin: forge.
forge
Multi-agent collaborative development workflow: Planner → Dev → Test → Learn with automatic bug-fix loops, test layering, and experience accumulation.