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 CATWILLgh/MAINFRAMEnpx agentmods add plugins/catwillgh/mainframe/plugingit clone --depth 1 https://github.com/CATWILLgh/MAINFRAMEGrade A, and why
mainframe 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": "mainframe",
"description": "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.",
"version": "0.1.0",
"author": {
"name": "CATWILLgh",
"url": "https://github.com/CATWILLgh"
},
"homepage": "https://github.com/CATWILLgh/MAINFRAME",
"license": "MIT"
}
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 b80f840b2a37
mainframe is a plugin published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 10d 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
claude-plugins
claude context tools - Claude Code plugins for context-size awareness: subagent context reporting, cross-session send guarding, and main-session compaction management incl. an opt-in tmux managed mode.
compact-manager
Warns the main session as its own context fills, captures a wake packet before compaction, and reorients the session after it — so an autonomous orchestrator survives past one context window.
cross-session-send-guard
Warns before, and can gate, a SendMessage to a large idle peer Claude Code session — a cold wake replays the peer's whole transcript at full price.
subagent-context
Reports each subagent's context size to the orchestrating agent and warns before an overloaded subagent gets re-tasked.
task-forensics
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.
google-plugins
Plugin marketplace listing 17 plugins: alloydb, alloydb-omni, bigtable, cloud-sql-mysql, cloud-sql-postgresql.