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/chiphwang1/oke-agent-plugin/agents-mdgit clone --depth 1 https://github.com/chiphwang1/oke-agent-pluginWhat 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 | $0.00570 | $0.00570 |
| Opus 5 | $0.00285 | $0.00285 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
oke-agent-plugin 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 yesterday.
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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OKE Agent Plugin - Codex Instructions
Repository Purpose
This repository is a dual-surface agent plugin for Oracle Kubernetes Engine (OKE). It supports Claude Code through .claude-plugin/plugin.json and Codex through .codex-plugin/plugin.json.
The plugin packages reusable skills for:
- Generating OKE Terraform and OCI Resource Manager assets.
- Troubleshooting OKE incidents with Kubernetes and OCI evidence.
- Creating GVA-enabled OKE node pools.
- Deploying and validating Multus multi-home pods on GVA-enabled node pools.
Repo Map
.codex-plugin/plugin.json- Codex plugin manifest. Keep it aligned with.claude-plugin/plugin.json..claude-plugin/plugin.json- Claude Code plugin manifest.skills/*/SKILL.md- Skill entrypoints and trigger descriptions.skills/*/references/- Longer skill reference material loaded only when needed.skills/*/scripts/- Deterministic helpers used by skills.scripts/- Shared shell helpers and smoke-test targets.tests/scripts-smoke.sh- Offline smoke tests; this must not require live OCI or Kubernetes access.README.md,PLAN.md,PRD.md,PRD-detailed.md- User-facing and planning documentation.
Working Rules
- Preserve both Codex and Claude compatibility when adding or changing skills.
- Keep skill frontmatter concise and trigger-oriented. The
descriptionshould say when the skill should be used. - Do not commit tenancy-specific OCIDs, private IPs, kubeconfig contents, auth tokens, or customer-specific cluster names into public examples.
- Prefer placeholder values in public docs, for example
<cluster_ocid>,<region>, and<node-name>. - Keep live OCI/OKE operations separate from offline repo tests. Smoke tests must use mocks or static inputs.
- Use fully qualified container images in OKE examples, for example
docker.io/nicolaka/netshoot:v0.13. - For OCI security-token workflows, show
OCI_CLI_AUTH=security_tokenor--auth security_tokenexplicitly. - If changing a skill workflow, update README and any matching PRD/PLAN sections when the user-facing behavior 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.
- yesterday First seen · 50 lines · 570 tokens per session scan A 410a61538c21
oke-agent-plugin AGENTS.md is an instructions file published in the GitHub repository chiphwang1/oke-agent-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 570 tokens to every session, about $0.0029 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
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.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.