agentmods.dev

malformed-plugin

A plugin described as evaluating Claude Code add-on parts, such as skills, agents, commands, and hooks. Its manifest is malformed, so the add-on's exact operation is unclear.

In plain words
What is it for?
Evaluating Claude Code plugin components after its manifest has been corrected.
Why use it?
It is intended to check whether those add-on parts trigger correctly, but the invalid manifest may prevent it from loading.

Plugin for Claude Code

2 yesterday A scan tokens not measured original MIT
View the source file imbflool/cc-plugin-eval
Install

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.

Claude Code
/plugin marketplace add imbflool/cc-plugin-eval
agentmods
npx agentmods add plugins/imbflool/cc-plugin-eval/malformed-plugin
Clone the repo
git clone --depth 1 https://github.com/imbflool/cc-plugin-eval

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

malformed-plugin 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.

tests/fixtures/malformed-plugin/.claude-plugin/plugin.json · 5 lines

What it actually says

{
  "name": "malformed-plugin",
  not valid json
}
Changes

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.

  1. yesterday First seen · 5 lines scan A defa47ed4c5d

Subscribe to this mod's changes

malformed-plugin is a plugin published in the GitHub repository imbflool/cc-plugin-eval (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.

Testingai-testinganthropicclaudeclaude-agent-sdkclaude-codecli
Related

Other plugins, from other repositories

copilotkit-tools

Plugin marketplace listing 1 plugin: aimock.

CopilotKit/aimock · not measured

aimock

Fixture authoring guidance for @copilotkit/aimock — LLM, multimedia, MCP, A2A, AG-UI, vector, and service mocking.

CopilotKit/aimock · not measured

qaskills

QASkills.sh — curated QA testing skills for AI coding agents. Browse 380+ skills at https://qaskills.sh or install individual skills with npx @qaskills/cli add .

PramodDutta/qaskills · not measured

orangepro

OrangePro local evidence graph, runtime coverage, and grounded test-generation MCP tools.

OrangeproAI/orangepro-mcp · not measured

visual-skills

AI film director skills: video and image prompting with dramaturgy-first methodology.

smixs/visual-skills · not measured

sorify

Automated E2E test generation for Sorify — explore a URL, generate Playwright test code, upload to Sorify, and run tests. Supports three granularity levels: small (page load check), medium (component layout check), fine (all condition axes with network mocks).

rakutentech/sorify · not measured