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/openshift/ols/agents-mdgit clone --depth 1 https://github.com/openshift/olsWhat 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 | $0.01028 | $0.01028 |
| Opus 5 | $0.00514 | $0.00514 |
| Sonnet 5 | $0.00206 | $0.00206 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
ols 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenShift Lightspeed — Workspace Guide for AI
Project Overview
OpenShift Lightspeed (OLS) is an AI-powered assistant for OpenShift. This workspace contains all repositories that make up the product. Each repo has its own AGENTS.md with repo-specific conventions — read it before working in that repo.
Repositories
| Repo | Purpose |
|---|---|
lightspeed-service |
Core backend — FastAPI service, LLM integration, RAG |
lightspeed-operator |
Kubernetes operator that deploys and manages the service |
lightspeed-console |
OpenShift console plugin (frontend UI) |
lightspeed-rag-content |
RAG corpus — OpenShift documentation for retrieval |
lightspeed-agentic-operator |
Operator for the agentic (MCP/tool-calling) variant |
lightspeed-agentic-console |
Console plugin for the agentic variant |
lightspeed-agentic-sandbox |
Sandboxed execution environment for agentic actions |
lightspeed-agentic-alerts-adapter |
Adapter bridging OpenShift alerts into the agentic system |
lightspeed-hub |
Multicluster hub — manages spoke clusters, coordinates fleet-wide agentic operations |
lightspeed-hub-ui |
Console UI for the multicluster hub |
lightspeed-otel-collector |
Custom OpenTelemetry collector for OLS observability |
lightspeed-team-harness |
Shared AI coding skills for the team |
ols-load-generator |
Load testing tool for the OLS service |
Cross-Repo Conventions
Jira
- Project key: OLS on
redhat.atlassian.net - All commit messages and PR titles start with
OLS-XXXX
Git Workflow
All repos use a fork-based workflow:
- Push to your fork, not
origin - PR against
origin/mainfrom<your-user>:<branch> - Squash commits before pushing
Auto-Push Spec PRs
After brainstorming writes and commits a spec change, auto-push and open a PR if the diff only touches spec/docs files. The PR is labeled kind/design for easy filtering — a human merges it.
Spec-only pattern: .ai/spec/**, docs/superpowers/specs/**. Never include AGENTS.md, CLAUDE.md, or any other file — changes to agent instructions or non-spec files always require human review.
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 · 72 lines · 1,028 tokens per session scan A e8ed2a6b52b4
ols AGENTS.md is an instructions file published in the GitHub repository openshift/ols (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,028 tokens to every session, about $0.0051 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.