ai-plugins GEMINI.md

Repository instructions explaining how the Endor Labs Agent Kit is distributed across different AI tools. They clarify which directory should be installed for Gemini CLI, a command-line AI assistant, and which workflows belong to the kit.

In plain words
What is it for?
Installing the correct Gemini extension and directing jobs such as security scanning, dependency review, CI/CD posture, configuration automation, and findings browsing.
Why use it?
They prevent installing the wrong repository directory and define the expected setup and tool choices for security and automation workflows.

Instructions file for Gemini CLI

Install

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.

agentmods
npx agentmods add instructions/endorlabs/ai-plugins/gemini-md
Clone the repo
git clone --depth 1 https://github.com/endorlabs/ai-plugins

Made for: Gemini CLI.

Per session 390 This file is loaded in full into every session.
When invoked 390 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00390 $0.00390
Opus 5 $0.00195 $0.00195
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 3d ago against content hash 57f73689c2b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-plugins GEMINI.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 3d 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.

GEMINI.md · 38 lines

What it actually says

Endor Labs Agent Kit Root Package

This repository root is a multi-host distribution surface, not a Gemini CLI extension root. Do not install the repository root as a Gemini extension.

Install Gemini CLI from plugins/gemini/endor-labs-agent-kit/ so Gemini discovers the generated Gemini skills from that extension's skills/ directory. Do not load the root Cursor skills as Gemini workflows.

Use Endor Labs Agent Kit workflows only within their generated safety contracts. Prefer endorctl agent api --agent-id <canonical-recipe-id> lookups when a workflow supports them. Use Endor MCP only when a selected MCP-capable workflow needs it or the user explicitly asks for it.

If setup, authentication, namespace, Endor MCP, endorctl, gh, or repository tooling is missing, use the endor-agent-kit-setup skill before live Endor work.

User jobs mapped to root skills:

  • AI SAST Remediation: use skill ai-sast-remediation.
  • CI/CD And Supply Chain Posture: use skill cicd-posture.
  • Configuration Automation: use skill configuration-automation.
  • Dependency Reviewer: use skill dependency-reviewer.
  • Findings Browser: use skill findings-browser.
  • Malware Responder: use skill malware-responder.
  • OSS Upgrade Investigator: use skill oss-upgrade-investigator.
  • Remediation Planning: use skill remediation-planning.
  • SCA Remediation: use skill sca-remediation.
  • Troubleshooting: use skill troubleshooting.
  • Vulnerability Explainer: use skill vulnerability-explainer.

Setup must not run scans, run endorctl host-check, edit shell profiles, auto-install gh, install language tooling, collect/write API secrets, or configure Endor MCP without explicit user approval.

Changes

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.

  1. 3d ago First seen · 38 lines · 390 tokens per session scan A 57f73689c2b6

Subscribe to this mod's changes

ai-plugins GEMINI.md is an instructions file published in the GitHub repository endorlabs/ai-plugins (9 stars, last pushed 6d ago), licensed MIT. It adds 390 tokens to every session, about $0.0019 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 2026-08-30.

Related

Other instructions, from other repositories

Sighthound AGENTS.md

Instructions for Corgea/Sighthound, covering claude, commands, python / django test naming and agent skill.

Corgea/Sighthound · 847 tokens

dotskills AGENTS.md

Instructions for vincentkoc/dotskills, covering agents.md, repository purpose, mandatory contribution flow, skill standards and openai metadata defaults.

vincentkoc/dotskills · 892 tokens

FMT-exocortex-template CLAUDE.md

Claude Code instructions for TserenTserenov/FMT-exocortex-template, covering инструкции для всех репозиториев, 1. архитектура репозиториев, 2. орз-фрактал (открытие → работа → закрытие), блокирующие правила and протокол работы (полный → memory/protocol-work.md).

TserenTserenov/FMT-exocortex-template · 4,800 tokens

asap-protocol AGENTS.md

AGENTS.md instructions for asap-protocol/asap-protocol, covering agents.md, project context, quick start, agent guidance (rules vs skills) and knowledge map.

asap-protocol/asap-protocol · 1,995 tokens

slipway AGENTS.md

Instructions for signalridge/slipway, covering slipway agent principles, user owns the process, investigate before clarifying, report, do not certify and maintain the whole surface.

signalridge/slipway · 470 tokens

ai-marketplace AGENTS.md

Instructions for Kong/ai-marketplace, covering skill authoring guide, what belongs here, before you create a skill, what a good skill does and layered skill design.

Kong/ai-marketplace · 5,562 tokens