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/paperclipinc/openclaw-operator/claude-mdgit clone --depth 1 https://github.com/paperclipinc/openclaw-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/paperclipinc/openclaw-operator/claude-md)<a href="https://agentmods.dev/instructions/paperclipinc/openclaw-operator/claude-md"><img src="https://agentmods.dev/badge/instructions/paperclipinc/openclaw-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 5.1 | $0.02569 | $0.02569 |
| Opus 5 | $0.01285 | $0.01285 |
| Sonnet 5 | $0.00514 | $0.00514 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade A, and why
openclaw-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 6d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — OpenClaw Kubernetes Operator
Project Overview
Go-based Kubernetes operator for managing OpenClaw instances, built with controller-runtime (kubebuilder). CRD API group is openclaw.rocks, version v1alpha1.
- Module:
github.com/paperclipinc/openclaw-operator - Go version: 1.25
- GitHub:
paperclipinc/openclaw-operator(GHCR org:paperclipinc)
Commands
make test # Unit + integration tests (requires envtest binaries)
make lint # golangci-lint
make build # Build manager binary
make manifests # Regenerate CRD YAML + RBAC after API type changes
make generate # Regenerate deepcopy methods after API type changes
make install # Install CRDs into current cluster
make run # Run operator locally against current cluster
go test ./internal/resources/ -v # Fast unit tests (no envtest needed)
go vet ./... # Go vet check
Architecture
api/v1alpha1/ → CRD types (OpenClawInstance)
internal/controller/ → Reconciliation logic (single controller)
internal/resources/ → Pure resource builder functions (Deployment, Service, etc.)
config/crd/bases/ → Generated CRD YAML (committed to git)
charts/ → Helm chart
bundle/ → OLM bundle for OperatorHub submissions
test/e2e/ → E2E tests (run against kind cluster)
Separation of concerns: Controller logic (internal/controller/) only orchestrates reconciliation. All resource construction happens in pure functions in internal/resources/. This makes builders easy to unit test without envtest.
Reconciliation Rules
These rules are enforced by CI (Reconcile Guard check) and must be followed:
Always use controllerutil.CreateOrUpdate for managed resources
Never call r.Update() or r.Create() directly on managed resources (Deployments, Services, ConfigMaps, etc.). Always use:
obj := &appsv1.Deployment{
ObjectMeta: metav1.ObjectMeta{
Name: resources.DeploymentName(instance),
Namespace: instance.Namespace,
},
}
_, err := controllerutil.CreateOrUpdate(ctx, r.Client, obj, func() error {
desired := resources.BuildDeployment(instance)
obj.Labels = desired.Labels
obj.Spec = desired.Spec
return controllerutil.SetControllerReference(instance, obj, r.Scheme)
})
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.
- 6d ago First seen · 219 lines · 2,569 tokens per session scan A b6a83bfc8b75
openclaw-operator CLAUDE.md is an instructions file published in the GitHub repository paperclipinc/openclaw-operator (396 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,569 tokens to every session, about $0.0128 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
openclaw-kubernetes AGENTS.md
Instructions for feiskyer/openclaw-kubernetes, covering agents.md, links, development commands, lint the chart against all values files and render templates to verify correctness (output discarded).
openclaw-kubernetes CLAUDE.md
Instructions for feiskyer/openclaw-kubernetes, covering claude.md, links, development commands, lint the chart against all values files and render templates to verify correctness (output discarded).
autocontext CLAUDE.md
Claude Code instructions for greyhaven-ai/autocontext, covering claude.md, project overview, repository layout, commands and setup.
autocontext AGENTS.md
AGENTS.md instructions for greyhaven-ai/autocontext, covering agent guide, pick the right surface, working directories, setup and parity-last changes.
atlasclaw AGENTS.md
AGENTS.md instructions for CloudChef/atlasclaw, covering agents.md - atlasclaw coding guidelines, build / test / lint commands, backend (python), run the service and run all tests.
souls-directory CLAUDE.md
Instructions for thedaviddias/souls-directory, covering claude.md — project context for ai assistants, project overview, tech stack, critical rules and database is convex.