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 technicalpickles/pickled-claude-pluginsnpx agentmods add plugins/technicalpickles/pickled-claude-plugins/sandbox-advisorgit clone --depth 1 https://github.com/technicalpickles/pickled-claude-pluginsGrade A, and why
sandbox-advisor 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": "sandbox-advisor",
"description": "Turns Claude Code sandbox EPERMs into crisp re-run-unsandboxed guidance"
}
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 · 5 lines scan A c30fccde2ff7
sandbox-advisor is a plugin published in the GitHub repository technicalpickles/pickled-claude-plugins (10 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
qiushi-skill
Qiushi Skill: methodology skills for AI agents guided by seeking truth from facts, with Claude Code, Cursor, OpenClaw, Codex, OpenCode, and Hermes guidance.
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.
kit
Spec-driven Claude Code workflow with verification pipeline. Hooks, slash commands, and verification subagents.
ticket-flow
Beads-backed ticket workflow for Claude Code: spec → pickup → implement → finish behind verdict and merge gates, orchestrated by /flow (--local with resume, --parallel, --serial/--loop unattended queue runner), each ticket in its own git worktree. Five visible commands; the phase skills are model-invoked.
superpowers-graph
The Superpowers software-development methodology executed as a guarded state machine: 21 typed nodes, 96 total exit guards, 9 bounded retry loops, durable run state that survives compaction, and a ledger recording every step that could not run.
atelier
Agent-orchestration plugin: a lead reviews a plan, gates on user approval, and routes tasks to specialist agents by capability.