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 melodic-software/claude-code-pluginsnpx agentmods add plugins/melodic-software/claude-code-plugins/actionlintgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsGrade A, and why
actionlint 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "actionlint",
"version": "0.8.26",
"description": "Lint GitHub Actions workflow files on edit via actionlint, surfacing findings as advisory context.",
"author": {
"name": "Melodic Software",
"email": "[email protected]"
},
"license": "MIT",
"keywords": [
"actionlint",
"github-actions",
"workflow",
"yaml",
"linter",
"hook"
],
"userConfig": {
"actionlint_enabled": {
"type": "boolean",
"title": "actionlint-check hook",
"description": "Lint GitHub Actions workflow files on edit via actionlint",
"default": true
},
"stdin_read_timeout": {
"type": "number",
"title": "Hook stdin read timeout (seconds)",
"description": "Idle bound on reading the hook payload from stdin — how long the pipe may go silent before the hook gives up and fails open",
"default": 2,
"min": 1
}
}
}
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 · 35 lines scan A c966f66a0b5b
actionlint is a plugin published in the GitHub repository melodic-software/claude-code-plugins (12 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 2026-08-30.
Other plugins, from other repositories
community-claude-plugins
Plugin marketplace listing 1 plugin: example-deployment.
adversarial-testing
Adversarial test generation that finds real bugs by inverting the reward structure.
collaborative-planning
Collaborative planning commands with iterative requirements gathering. Ensures thorough understanding before implementation through structured Q&A sessions.
local-llm
Manage local Ollama LLM models for development and testing.
norvig-patterns
54 elegant coding patterns derived from Peter Norvig's pytudes. Guides Claude to write cleaner, more Pythonic code using proven patterns for algorithms, data structures, testing, and code structure.
collaborative-spec-builder
Collaborative specification building with iterative Q&A before implementation.