g5k-kickstart AGENTS.md

g5k-kickstart AGENTS.md is an instructions file for Codex, OpenCode from 0nyr/g5k-kickstart. It costs 535 tokens per session, scanned A, original, MIT.

Repository instructions for agents working on 0nyr/g5k-kickstart, a kit for running experiments on the Grid’5000 research testbed. They explain the project layout, operating rules, and conventions.

In plain words
What is it for?
Use them when reserving, launching, monitoring, synchronizing, or cleaning up Grid’5000 experiments, or when following the repository’s dry-run, smoke-run, and full-run approach.
Why use it?
They tell an agent where the operational guidance, documentation, and example experiment are located before it changes or runs anything.

Instructions file for CodexOpenCode

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/0nyr/g5k-kickstart/agents-md
Clone the repo
git clone --depth 1 https://github.com/0nyr/g5k-kickstart

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for g5k-kickstart AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/0nyr/g5k-kickstart/agents-md.svg)](https://agentmods.dev/instructions/0nyr/g5k-kickstart/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/0nyr/g5k-kickstart/agents-md"><img src="https://agentmods.dev/badge/instructions/0nyr/g5k-kickstart/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 535 This file is loaded in full into every session.
When invoked 535 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 5.1 $0.00535 $0.00535
Opus 5 $0.00267 $0.00267
Sonnet 5 $0.00107 $0.00107
Haiku 4.5 $0.00053 $0.00053

Measured 5d ago against content hash e0e1f5b4ef4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

g5k-kickstart 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 5d 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.

AGENTS.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — g5k-kickstart

Instructions for AI coding agents (Claude Code, Codex, ...) working in or from this repository.

What this repository is

A kickstart kit for running experiment campaigns on the Grid'5000 testbed. It packages the operational knowledge as an agent skill, human documentation, and a runnable example experiment.

Where to look

  • skills/g5k/SKILL.md is the operational core: golden rules, agent operating modes, OAR cheatsheet, non-interactive SSH patterns, distributed-run methodology, cleanup protocol. If you are about to touch Grid'5000 in any way (reserve, launch, monitor, sync, clean), read it first and follow it.
  • docs/ holds the longer human-readable guides (getting started, usage policy, running experiments, storage and sync, MAMUT-routing worked example).
  • example/ is a fully runnable toy experiment demonstrating the dry-run, smoke-run, full-run methodology with GNU parallel, locally and on g5k.

Claude Code users should install this repo as a plugin (see README.md), which exposes the skill as /g5k-kickstart:g5k. Agents without plugin support can simply read skills/g5k/SKILL.md.

Hard rules for agents operating Grid'5000

These are restated here because they are the ones that protect the account:

  1. Never run compute on a frontend. Experiments only run inside OAR jobs.
  2. Never install or launch an AI agent, LLM runtime, or IDE server on a g5k frontend or node. Agents drive g5k remotely over SSH from the user's machine.
  3. Respect the day/night usage policy: weekday jobs must not cross the 9:00 and 19:00 boundaries (exceptions in the skill), campaigns go to nights and weekends.
  4. Release idle reservations, report every oarsub you place to the user, and clean the remote home after each campaign (sync back, verify, delete).
  5. Fill in or ask for the user configuration (login, project, site, cluster) before issuing any g5k command.

Conventions in this repository

  • Prose in Markdown files is written one paragraph per physical line (editor soft-wrap), never hard-wrapped to a column width.
  • Commands in docs use <login>, <site>, <cluster>, <JOB_ID> placeholders; keep them generic, personal values do not belong in this repo.

Read the full file on GitHub · 31 lines

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. 5d ago First seen · 31 lines · 535 tokens per session scan A e0e1f5b4ef4f

Subscribe to this mod's changes

g5k-kickstart AGENTS.md is an instructions file published in the GitHub repository 0nyr/g5k-kickstart (1 stars, last pushed 1mo ago), licensed MIT. It adds 535 tokens to every session, about $0.0027 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.

Related

Other instructions, from other repositories

river-review GEMINI.md

Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.

s977043/river-review · 318 tokens

living-manual CLAUDE.md

Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.

dougstanford/living-manual · 1,108 tokens

ship-it open-pr.instructions.md

Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…

khrichtchatyi/ship-it · 84 tokens

agent-skills CLAUDE.md

Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.

mindbox-cloud/agent-skills · 1,143 tokens

my-claude-skills CLAUDE.md

Instructions for brody-0125/my-claude-skills, covering claude code skills repository, validation commands, sub-kopring-engineer: kotlin/java 코드 컨벤션 검증, numerical: 수치 연산 코드 검증 and sub-test-engineer: 문서 일관성 검증.

brody-0125/my-claude-skills · 1,093 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens