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 msshives-gif/claude-pluginsnpx agentmods add plugins/msshives-gif/claude-plugins/task-forensicsgit clone --depth 1 https://github.com/msshives-gif/claude-pluginsGrade A, and why
task-forensics 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": "task-forensics",
"version": "0.1.0",
"description": "Wraps background Bash tasks in a signal-forensics wrapper: when something kills a task, the killer's pid, uid, and cmdline are logged before the task dies.",
"author": {
"name": "msshives-gif"
},
"license": "MIT",
"homepage": "https://github.com/msshives-gif/claude-plugins/tree/main/plugins/task-forensics",
"repository": "https://github.com/msshives-gif/claude-plugins"
}
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 · 12 lines scan A e4eaae7a636b
task-forensics is a plugin published in the GitHub repository msshives-gif/claude-plugins (2 stars, last pushed 4d 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
mainframe
Personal hub of global Claude Code customizations — skills, hooks, and commands — that take effect across every project on the machine. Author's personal-use tool, published under MIT.
probity
Plugin marketplace listing 1 plugin: probity.
ballast
Builds up to a goal in a field you have no expertise in — learns the foundations it needs and keeps every solved path for the next goal.
hush
Trims command output, logs, and Claude's play-by-play before they pile up in the session, so long, noisy work stays quiet and readable. Install and forget — nothing to configure. Short questions with nothing to run cost a little more.
nunchi-marketplace
JIT rule-delivery plugin — compiles CLAUDE.md rules into trigger-bound hooks.
badi
Workflow management for Claude Code, Cursor, Gemini, Windsurf, AGENTS.md — 30 AI agents, 86 commands, 14 hooks, 63 opt-in skill categories. Built for Anthropic Claude Opus 4.7 and Sonnet 4.6.