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 mohammad19974/bounded-relaynpx agentmods add plugins/mohammad19974/bounded-relay/claude-code-plugingit clone --depth 1 https://github.com/mohammad19974/bounded-relayGrade A, and why
boundedrelay 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": "boundedrelay",
"version": "0.1.0",
"description": "Optional Claude Code coordinator skills for BoundedRelay adaptive Spec Kit delivery.",
"author": {
"name": "BoundedRelay contributors"
},
"license": "MIT",
"keywords": ["boundedrelay", "codex", "spec-kit", "sdd", "review"]
}
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 · 11 lines scan A 45e5c0ed8f59
boundedrelay is a plugin published in the GitHub repository mohammad19974/bounded-relay (1 stars, last pushed 3d 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
stop-that-shit
Keep Claude Code on task with local-first mode, scope, dependency, hash, and delegation guardrails.
sentinel
Install Sentinel's business-first computer vision delivery copilot.
kardebadas-claude-plugin
Personal plugins for Codex and Claude Code.
superb
Personal skill collection. Skills are invoked as superb: . craft turns a vague product idea into a decision-rich CRAFT.md brief — it questions, challenges and records, and deliberately stops short of planning. pipeline takes a settled idea to a finished branch, composing the superpowers skills with a zero-assumpt.
tokendiet
TokenDiet by Fortytude — free, open-source LLM-cost audit for your codebase. Type /tokendiet and your own agent finds where your code overpays for AI API calls (missing prompt caching, uncapped retries, prompt bloat, no batching) and hands you a concrete fix plan. Runs locally on your agent; nothing leaves your…
tokendiet
Audit your codebase for wasteful, expensive LLM API usage and get a concrete plan to cut the cost — cache, batching, model routing, retry caps, prompt bloat. Runs on your own agent, in your own repo. Free & open source. TokenDiet by Fortytude.