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 fledgeling-co/fledgeling-pluginsnpx agentmods add plugins/fledgeling-co/fledgeling-plugins/create-skillgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsGrade A, and why
create-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": "create-skill",
"description": "Build a brand-new skill from scratch: a broad clarifying interview that pins down trigger, output and done condition before anything is written, paid+free deep research on the skill's domain (read in full, citations verified), the build itself run through skill-creator with every structural choice traced to evidence, proof against a no-skill baseline with structural evals and a blind multi-family judge panel, then the full brand treatment and ship. The sibling of improve-skill, for when there is no predecessor to improve. v1.3.0 hardens the brand phase, which is where this pipeline was quietly skippable: a bundled `render_banner.py` renders banner-src.html and asserts the five things that fail silently (viewport override took effect, web font actually loaded, every image decoded, nothing overflows the frame, PNG is exactly 3200x1040), the marketplace catalogue gate now fails on a missing banner, and the pipeline has answers for three cases it previously had none for: the user forbidding questions, an existing in-repo research corpus that makes a second panel redundant, and a skill that joins an existing plugin rather than getting one of its own.",
"version": "1.4.1",
"author": {
"name": "Fledgeling",
"email": "[email protected]"
}
}
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 · 10 lines scan A a3148ad48b1f
create-skill is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed yesterday), 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
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
nextjs
Official Claude Code plugin marketplace for Next.js, serving the skills that ship in the vercel/next.js repository.
claude-plugins-official
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins
Plugin marketplace listing 97 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
ecc
Plugin marketplace listing 1 plugin: ecc.
ecc
Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses.