Agent Sandbox is a Kubernetes extension for managing isolated, stateful workloads that run as single long-lived containers with stable identities and persistent storage. It is intended for AI agent runtimes, reinforcement-learning workloads, and other applications that do not fit ordinary stateless deployments. Its catalogue skills and instructions support operating these sandbox workloads.
Borrowing it
Nothing to install: this file belongs to kubernetes-sigs/agent-sandbox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kubernetes-sigs/agent-sandbox/main/.agents/skills/dev-rules/SKILL.mdgit clone --depth 1 https://github.com/kubernetes-sigs/agent-sandboxWrote 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/skills/kubernetes-sigs/agent-sandbox/dev-rules)<a href="https://agentmods.dev/skills/kubernetes-sigs/agent-sandbox/dev-rules"><img src="https://agentmods.dev/badge/skills/kubernetes-sigs/agent-sandbox/dev-rules/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/skills/kubernetes-sigs/agent-sandbox/dev-rules"><img src="https://agentmods.dev/badge/skills/kubernetes-sigs/agent-sandbox/dev-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00013 | $0.00388 |
| Opus 5.5 | $0.00005 | $0.00155 |
| Sonnet 5.5 | $0.00003 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
dev-rules 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 1mo 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
Development Rules
Purpose
This skill ensures that AI agents contributing to this project follow project-specific rules regarding code review and style to maintain compliance and quality.
Instructions
- Go Development: Follow standard Kubernetes Go patterns and best practices.
- AI-Assisted Code Reviews:
- Do NOT directly apply code suggestions from CodeRabbit (or any AI review bot) via the GitHub UI. Doing so adds the AI bot as a co-author to the commit. Since AI bots cannot sign the Kubernetes CLA, this will cause the CLA check to fail and block the PR. Manual review and application of suggestions are required.
- Once the initial AI review (e.g., by CodeRabbit) is complete, ensure all review comments are addressed and resolved so the PR is ready for maintainers.
- API Conventions: Always use the
k8s-api-conventionsskill when modifying APIs. - Creating Pull Requests: When creating a Pull Request, always use and fill out the project's PR template (
.github/pull_request_template.md).- Description: Provide a clear and concise description in the "What this PR does" section.
- Related Issues: Link related issues using "Fixes #issue" or "Ref link".
- Release Notes: Fill out the
release-noteblock. Note that automated release notes are generated from the description in the first section, so ensure it is comprehensive. For breaking changes, describe required actions and ask the maintainers to label the PR withrelease-note-action-required.
References
- Project rules (as documented in
CONTRIBUTING.md)
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.
- 1mo ago Changed 56250446bf35
- 1mo ago First seen · 24 lines · 13 tokens per session scan A 6eb5197bee2d
dev-rules is a skill published in the GitHub repository kubernetes-sigs/agent-sandbox (4,346 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 388 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
troubleshoot-sandbox
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.
harness-design-fuzzing
Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2 multi-component / T3 full build), systematic input exploration, the two-coverage distinction (fuzzer-feedback vs audit)…
memory-safety-c-cpp
Reference vocabulary for memory-safety vulnerabilities in native C/C++ code — bug-class taxonomy, common arithmetic patterns that lead to corruption, dispatch-family discipline, type-confusion idioms, use-after-free patterns, and exploitability factors. Read when analyzing, hypothesizing, designing harnesses for, or…
vulnerability-triage
Reference vocabulary for interpreting vulnerability findings — detector-vs-impact distinction, severity anchoring on demonstrated evidence, the eleven-item interpretation rubric, delegation transparency, primitive-extent scaling, the disqualifier taxonomy (D-0..D-4), CVSS Achievable / Environmental framing…
04-security
A security and operations guide for deploying Dify, an open-source platform for building AI applications, in production.
open_rca_diagnosis
A structured method for finding the root cause of failures in microservices by examining measurements, request traces, and logs. It uses thresholds and cross-checks to connect symptoms to causes.