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/0nyr/g5k-kickstart/agents-mdgit clone --depth 1 https://github.com/0nyr/g5k-kickstartWrote 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/0nyr/g5k-kickstart/agents-md)<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>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 | $0.00535 | $0.00535 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
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.
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.mdis 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:
- Never run compute on a frontend. Experiments only run inside OAR jobs.
- 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.
- 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.
- Release idle reservations, report every
oarsubyou place to the user, and clean the remote home after each campaign (sync back, verify, delete). - 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.
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.
- 5d ago First seen · 31 lines · 535 tokens per session scan A e0e1f5b4ef4f
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.
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.
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.
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…
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.
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.
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.