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.
git clone --depth 1 https://github.com/xrgarcia/slashbin-ai-teamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/xrgarcia/slashbin-ai-team/skill-pack)<a href="https://agentmods.dev/plugins/xrgarcia/slashbin-ai-team/skill-pack"><img src="https://agentmods.dev/badge/plugins/xrgarcia/slashbin-ai-team/skill-pack/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/xrgarcia/slashbin-ai-team/skill-pack"><img src="https://agentmods.dev/badge/plugins/xrgarcia/slashbin-ai-team/skill-pack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
slashbin-harness 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 16d 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": "slashbin-harness",
"version": "2.3.0",
"description": "Skills owned by the slashbin-ai-team harness, available to every bot it runs."
}
What it installs
The manifest is a name and a version. 4 skills, 1 hook travel with it, and installing the plugin installs all of them — 284 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 16d ago Changed 2db0393d5e89
- 23d ago Changed ba2654f4ea48
- 1mo ago First seen · 6 lines scan A baecafda6602
slashbin-harness is a plugin published in the GitHub repository xrgarcia/slashbin-ai-team (13 stars, last pushed 6d 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 2026-08-30.
Other plugins, from other repositories
jarvis-deep-interview
Convergent Socratic interview with mathematical ambiguity gating. 8-15 narrowing rounds + Contrarian/Simplifier Challenge Mode + JSONL decision log. Inspired by Sorbh/interview-me.
jarvis-plan-review
11-section rigorous design plan review (problem, scope, architecture, security, observability, deployment, performance, reliability, testing, maintainability, migration). Adapted from gstack /plan-ceo-review for sole-developer + AI-pair-programming workflows.
discord-mcp
Discord bot bridge session context.
zalo
Zalo channel for Claude Code. Messaging bridge with built-in access control: manage pairing, allowlists, and group grants via /zalo: skills.
idfa-financial-architect
Intent-Driven Financial Architecture (IDFA) — build financial models that are human-readable, AI-operable, and audit-proof. Auto-activates on financial modelling tasks.
openclaw-cc
Autonomous AI assistant with 3-tier persistent memory, knowledge graph, 21 workflow skills, and multi-agent orchestration via Discord/Telegram.