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/lensapp/openshell-k8s-operator/claude-mdgit clone --depth 1 https://github.com/lensapp/openshell-k8s-operatorWrote 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/lensapp/openshell-k8s-operator/claude-md)<a href="https://agentmods.dev/instructions/lensapp/openshell-k8s-operator/claude-md"><img src="https://agentmods.dev/badge/instructions/lensapp/openshell-k8s-operator/claude-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 | $0.00828 | $0.00828 |
| Opus 5 | $0.00414 | $0.00414 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
openshell-k8s-operator CLAUDE.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 4d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for AI agents (and humans) working in this repository.
What this is
A Kubernetes operator providing declarative CRDs over an OpenShell gateway's gRPC
control plane. It is a thin front-end: it translates custom resources into
gateway API calls and mirrors gateway state back into .status. It does not
reimplement the gateway.
Status: OpenShellSandbox (create/get/delete), Provider (static credentials
from a Secret, entitlement-checked, synced with a rotation watch), Policy
(a reusable policy document validated by the gateway parser and applied to a
sandbox at creation via policyRef), OpenShellWorkspace (a cluster-scoped
gateway tenancy boundary with declarative membership, joined by sandboxes and
providers via spec.workspace), and OpenShellProviderProfile (a
cluster-scoped, platform-scoped provider type definition — spine-typed with
opaque arrays validated by the gateway's openshell-providers parser, imported
and updated in place) reconcilers. Sandbox, Provider, Workspace, and
ProviderProfile use finalizer-based cleanup; Policy owns no gateway state, so it
has none. Workspace-scoped provider profiles, and Providers v2 (gateway-managed
OAuth2 refresh), are deferred.
The repo is a Cargo workspace with two crates: crates/operator (the operator)
and crates/issuer (a small static OIDC issuer — mint + serve subcommands —
that the Helm chart bundles to mint the operator's gateway bearer). The operator
authenticates to the gateway with an OIDC bearer, runs lease-based leader
election, and serves /healthz + /readyz probes.
Build / test / lint
cargo build
cargo test
cargo clippy --all-targets # pedantic + nursery; must be clean
cargo fmt --check
cargo run --bin crdgen > deploy/charts/openshell-operator/files/crds.yaml # regenerate CRD manifests
Conventions
- Follow OpenShell's Rust conventions (its
STYLEGUIDE.md). - SPDX license headers on every source file (Apache-2.0).
- Clippy
all+pedantic+nurseryat warn (seeCargo.toml+clippy.toml); keep the tree warning-free rather than sprinkling#[allow]. - Public config/enum types are
#[non_exhaustive]. - Regenerate the CRD manifest after any change to
crates/operator/src/crd.rs.
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.
- 4d ago First seen · 71 lines · 828 tokens per session scan A f8786d95dee9
openshell-k8s-operator CLAUDE.md is an instructions file published in the GitHub repository lensapp/openshell-k8s-operator (25 stars, last pushed 2d ago), licensed Apache-2.0. It adds 828 tokens to every session, about $0.0041 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 2026-08-30.
Other instructions, from other repositories
OpenSandbox AGENTS.md
AGENTS.md instructions for opensandbox-group/OpenSandbox, covering opensandbox agents, repository map, routing, working principles and guardrails.
OpenSandbox CLAUDE.md
Claude Code instructions for opensandbox-group/OpenSandbox: See AGENTS.md for all rules, routing, and conventions.
agent-sandbox AGENTS.md
AGENTS.md instructions for kubernetes-sigs/agent-sandbox, covering agents.md, project summary, repository layout, agent skills and build, test, lint.
agent-sandbox copilot-instructions.md
Copilot instructions for kubernetes-sigs/agent-sandbox: Project Context & Architecture: Refer to AGENTS.md for full project background, module layout, toolchain versions, and core conventions.
mariadb-operator AGENTS.md
AGENTS.md instructions for mariadb-operator/mariadb-operator, covering agents.md, project overview, simplicity, crds and repository structure.
ogo AGENTS.md
AGENTS.md instructions for aknochow/ogo, covering ogo - project context, documentation - read first, what this is, versioning - critical and tag strategy.