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/aknochow/ogo/agents-mdgit clone --depth 1 https://github.com/aknochow/ogoWhat 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 | $0.00945 | $0.00945 |
| Opus 5 | $0.00473 | $0.00473 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
ogo 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 3d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OGO - Project Context
Documentation - READ FIRST
Before asking the user about architecture, CRDs, configuration, or deployment - check the docs. They have answers to most questions.
- docs/ - full documentation (concepts, guides, reference, examples)
- docs/index.md - navigation index
- README.md - same content as docs/index.md
- CLAUDE.md - routes here
What This Is
OGO (OpenShift Gateway Operator) deploys and manages NVIDIA OpenShell Gateway instances on OpenShift. It automates TLS, RBAC, SCC, Routes, Envoy Gateway ingress, and provides an auth-bridge for OpenShift SSO login.
Versioning - CRITICAL
Semantic versioning. Base version is 0.1.0 in the Makefile.
- NEVER bump the semver unless the user explicitly says to
- Git tags drive releases:
git tag v0.1.0 && git push origin v0.1.0 - VERSION in Makefile stays as base — CI overrides from the git tag
- No calver dev tags —
:mainis the rolling dev build
Tag Strategy
| Event | Image tags |
|---|---|
| Push to main | :main |
Release (v0.1.0) |
:v0.1.0 + :latest |
Pre-release (v0.2.0-rc1) |
:v0.2.0-rc1 |
| Dependency-only bump (OpenShell version pin) | :vX.Y.Z-N (auto-tagged on merge; N increments per bump since the last real release, resets when one is cut) |
Dependency-only bumps don't touch :latest — only a deliberate vX.Y.Z
release does. See hack/openshell-pins/Dockerfile and
.github/workflows/upstream-sync.yml for how these are detected
(Dependabot) and tagged (auto, since no OGO code changes).
Image Ownership - DO NOT CONFUSE
| Image | Owner | Tags |
|---|---|---|
quay.io/aknochow/ogo |
Us | Our semver |
quay.io/aknochow/ogo-auth-bridge |
Us | Our semver |
ghcr.io/nvidia/openshell/gateway |
NVIDIA | Their tags (latest, v0.0.73) |
ghcr.io/nvidia/openshell/supervisor |
NVIDIA | Their tags |
NEVER tag NVIDIA images with our tags.
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.
- 3d ago First seen · 95 lines · 945 tokens per session scan A b8aa65708355
ogo AGENTS.md is an instructions file published in the GitHub repository aknochow/ogo (10 stars, last pushed 6d ago), licensed Apache-2.0. It adds 945 tokens to every session, about $0.0047 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
mariadb-operator AGENTS.md
Instructions for mariadb-operator/mariadb-operator, covering agents.md, project overview, simplicity, crds and repository structure.
mariadb-operator CLAUDE.md
Instructions for mariadb-operator/mariadb-operator, a project described as: 🦭 Run and operate MariaDB in a cloud native way.
bex CLAUDE.md
Instructions for bex-co/bex, covering claude.md, repo map, commands, local cluster workflow and environment variables.
inference-gateway AGENTS.md
Instructions for inference-gateway/inference-gateway, covering agents.md, commands, code generation, architecture and conventions.
kubernetes-mcp-server AGENTS.md
AGENTS.md instructions for containers/kubernetes-mcp-server, covering project agents.md for kubernetes mcp server, project structure, feature development, logging and adding new mcp tools.
openshell-k8s-operator CLAUDE.md
Instructions for lensapp/openshell-k8s-operator, covering claude.md, what this is, build / test / lint, conventions and layout.