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 thesepehrm/offstagenpx agentmods add plugins/thesepehrm/offstage/marketplacegit clone --depth 1 https://github.com/thesepehrm/offstageGrade A, and why
offstage 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 2d ago.
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": "offstage",
"owner": {
"name": "offstage"
},
"plugins": [
{
"name": "offstage-qa",
"source": "./",
"description": "Background QA for macOS apps: AX perception, semantic port actuation, canonical pixel goldens, ground-truth verification."
}
],
"description": "Background QA for macOS apps with the offstage harness."
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 15 lines scan A 27dfd591cfa2
offstage is a plugin published in the GitHub repository thesepehrm/offstage (5 stars, last pushed 15d 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
kiln
Multi-model software creation pipeline. A conversation becomes running, tested software — an interactive brainstorm, then an autonomous build: GPT-5.6 writes the code, Claude shapes the plans and interfaces, and each family inspects the work of the other.
claude-bionify
Bionic reading for Claude's responses that bolds the leading part of each word to guide your eyes and enable you to read faster.
claude-wp-builder
WordPress site-building methodology: demo HTML → custom theme with ACF/SCF, bilingual support, section-by-section building.
rad-chrome-extension
MV3 Chrome extension development standards (WXT, React, TypeScript) with two pure-stdlib Python validators that catch what LLM eyeballing misses. Skills cover architecture, MV3 security (CSP, remote code ban, content script isolation), permission minimization and CWS compliance, typed messaging, storage selection…
claude-speak
Plugin marketplace listing 1 plugin: claude-speak.
superpipelines-marketplace
Marketplace for the superpipelines plugin: design and run multi-agent AI pipelines.