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 TechSpokes/skill-base-templatenpx agentmods add plugins/techspokes/skill-base-template/claude-plugingit clone --depth 1 https://github.com/TechSpokes/skill-base-templateGrade A, and why
placeholder-skill 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.
What it actually says
{
"name": "placeholder-skill",
"displayName": "Placeholder Skill",
"version": "0.1.0",
"description": "Placeholder plugin manifest for a generated agent skill.",
"author": {
"name": "Template Author"
},
"homepage": "https://github.com/OWNER/REPOSITORY",
"repository": "https://github.com/OWNER/REPOSITORY",
"license": "MIT",
"keywords": [
"agent-skill",
"claude-plugin"
]
}
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 First seen · 17 lines scan A 0e9421f50eed
placeholder-skill is a plugin published in the GitHub repository TechSpokes/skill-base-template (4 stars, last pushed 1mo 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
roadtrip-skill
Plugin marketplace listing 1 plugin: roadtrip-navigator.
swift-focusengine-pro
Plugin marketplace listing 1 plugin: swift-focusengine-pro.
ezra-governed
Six governed agent skills: reasoning-doctrine, governed-operator, write-maintainable-code, portable-adaptive-planning, test-verification, and ship-it-or-fix-it. The agent that builds a thing never approves it.
mixedbread-skills
Plugin marketplace listing 5 plugins: mxbai-cli, mixedbread-search, mixedbread-parsing, mixedbread-search-agent, mixedbread-search-agent-harness.
multica-ops
Mops (Executive Advisor) for Multica: builds and runs an autonomous company of AI agents — interview, bootstrap, conveyor, console.
render-visual-skill
Designed PNGs from HTML — diagrams, slides, social cards, code snippets, device mockups and animated sequence GIFs.