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.
npx agentmods add instructions/adamanz/grok-bot-skill/agents-mdgit clone --depth 1 https://github.com/adamanz/grok-bot-skillWrote 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/instructions/adamanz/grok-bot-skill/agents-md)<a href="https://agentmods.dev/instructions/adamanz/grok-bot-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/adamanz/grok-bot-skill/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00114 | $0.00114 |
| Opus 5 | $0.00057 | $0.00057 |
| Sonnet 5 | $0.00023 | $0.00023 |
| Haiku 4.5 | $0.00011 | $0.00011 |
Grade A, and why
grok-bot-skill AGENTS.md 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 6d 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
Grok Bot Skill
This repository is an Agent Skill for the xAI Grok Bot desktop app.
Install:
npx skills add adamanz/grok-bot-skill -g
When the user wants to chat with a Grok Bot, list Grok Bots, create a new Grok Bot teammate, or operate Grok Bot from the terminal, follow SKILL.md and run scripts/grokbot.py. Do not use the Cursor Cloud Agents API.
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.
- 6d ago First seen · 12 lines · 114 tokens per session scan A 9119c5e4dba0
grok-bot-skill AGENTS.md is an instructions file published in the GitHub repository adamanz/grok-bot-skill (8 stars, last pushed 19d ago), licensed MIT. It adds 114 tokens to every session, about $0.0006 per session on Opus 5. 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 instructions, from other repositories
datavault4dbt-agent-skills CLAUDE.md
Instructions for ScalefreeCOM/datavault4dbt-agent-skills, covering datavault4dbt agent skills — repository guide, what a skill is, skill requirements, writing good datavault4dbt skills and handling external content.
sapcc-skill AGENTS.md
AGENTS.md instructions for eljoujat/sapcc-skill, covering agents.md, project overview, repository structure, key file: scripts/execute.js and execution flow.
governed-agent-skills CLAUDE.md
Claude Code instructions for Ezra144israel/governed-agent-skills: Read AGENTS.md. It governs this repository.
databricks-logs-reader CLAUDE.md
Instructions for zencity/databricks-logs-reader, covering dbr-logs, commands, architecture and gotchas.
agent-kit AGENTS.md
AGENTS.md instructions for work0r-ai/agent-kit, covering agents.md, structure, maintenance rules, validation and clawmem — semantic code memory.
agent-kit CLAUDE.md
Claude Code instructions for work0r-ai/agent-kit, covering workorai-agent-kit — agent instructions, implementation protocol, preconditions (first step), 1. prior-art search (before planning) and 2. diary (.tasks/, gitignored).