agentmods.dev

obol-stack CLAUDE.md

Repository instructions for Obol Stack, a system that runs AI agents and decentralised infrastructure locally. They describe its cluster, command-line interface, payment-gated inference, conventions, and review expectations.

In plain words
What is it for?
Use them when developing or reviewing Obol Stack components such as agents, Kubernetes resources, blockchain networks, Cloudflare tunnels, or payment flows.
Why use it?
They explain the project’s required environment and rules before changes are made, including its local cluster, host Ollama service, branch naming, and security boundaries.

Instructions file

11 3d ago C scan 16,508 tokens original Apache-2.0
View the source file ObolNetwork/obol-stack
Install

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.

agentmods
npx agentmods add instructions/obolnetwork/obol-stack/claude-md
Clone the repo
git clone --depth 1 https://github.com/ObolNetwork/obol-stack
Per session 16,508 This file is loaded in full into every session.
When invoked 16,508 The same file — it is already loaded in full.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.16508 $0.16508
Opus 5 $0.08254 $0.08254
Sonnet 5 $0.03302 $0.03302
Haiku 4.5 $0.01651 $0.01651

Measured 2d ago against content hash d09cb6f0a357, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

obol-stack CLAUDE.md scanned grade C with 2 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

just clean # rm -rf bin/ .workspace/bin/

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**x402-buyer is distroless** — no `wget`, `curl`, or shell. Use port-forward (`svc/x402-buyer`), not `kubectl exec`.
CLAUDE.md · 524 lines

How it starts

The opening of the file, as written. The whole thing — 524 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Overview

Obol Stack: AI agents running decentralised infra locally. k3d cluster + Hermes default agent + optional OpenClaw instances + blockchain networks + payment-gated inference (x402) + Cloudflare tunnels. CLI: github.com/urfave/cli/v3.

Conventions

  • Commits: Conventional commits — feat:, fix:, docs:, test:, chore:, security: with optional scope.
  • Branches: feat/, fix/, research/, docs/, chore/ prefixes.
  • GitHub branch policy: NEVER push codex/-prefixed branches to GitHub; rename to a non-codex prefix first.
  • Architecture reference: @.claude/skills/obol-stack-dev/SKILL.md (invoke via /obol-stack-dev).
  • Review scope: No broad/vague boundaries. State exact files, invariants, expected evidence. Prefer concrete checks ("controller cannot access signer/Secrets", "agent write RBAC is namespace-scoped", "flow uses real obol CLI path") over generic "review architecture".
  • Planning vs user docs: plans/ -> implementation plans, design notes, retrospectives. docs/ -> durable user-facing docs. Don't mix.
  • Release descriptions: Use .github/release-template.md. The release workflow creates a draft with generated notes; rewrite the narrative body from the template. Keep generated What's Changed, New Contributors, and Full Changelog sections at the bottom. NEVER include private keys, seed phrases, passwords, hostnames, personal paths, or raw bearer tokens.

Build, Test, Run

just build                                    # build with version info
go build -o .workspace/bin/obol ./cmd/obol    # build to .workspace/bin/obol
go build ./...                                # check compilation
go test ./...                                 # all unit tests
go test -v -run 'TestName' ./internal/pkg/    # single test

# Integration tests (//go:build integration; skip when prerequisites missing)
# Requires running cluster + host Ollama
export OBOL_DEVELOPMENT=true OBOL_CONFIG_DIR=$(pwd)/.workspace/config OBOL_BIN_DIR=$(pwd)/.workspace/bin OBOL_DATA_DIR=$(pwd)/.workspace/data
go build -o .workspace/bin/obol ./cmd/obol    # MUST rebuild after code changes
go test -tags integration -v -timeout 15m ./internal/openclaw/

# Paid-inference commerce loop — needs host Ollama qwen3.5:9b
# Does NOT replace release-gate flows 11/13/14 (those require OBOL_LLM_ENDPOINT → vLLM/llama.cpp)
# Reuse worktree cluster: export OBOL_CONFIG_DIR=<worktree>/.workspace/config
go test -tags integration -v -run TestIntegration_Tunnel_SellDiscoverBuySidecar_QuotaAndBalance -timeout 30m ./internal/openclaw/

# Release-gate buyer/seller smoke — needs OBOL_LLM_ENDPOINT → OpenAI-compatible vLLM/llama.cpp
RELEASE_SMOKE_INCLUDE_OBOL=true RELEASE_SMOKE_INCLUDE_OBOL_FORK=true \
  OBOL_LLM_ENDPOINT=http://127.0.0.1:8000/v1 OBOL_LLM_MODEL=qwen36-deep \
  bash flows/release-smoke.sh

just up    # obol stack init → up
just down  # obol stack down → purge
just clean # rm -rf bin/ .workspace/bin/

OBOL_DEVELOPMENT=true ./obolup.sh  # one-time dev setup (uses .workspace/, go run wrapper)

Read the full file on GitHub · 524 lines

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.

  1. 2d ago First seen · 524 lines · 16,508 tokens per session scan C d09cb6f0a357

Subscribe to this mod's changes

obol-stack CLAUDE.md is an instructions file published in the GitHub repository ObolNetwork/obol-stack (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 16,508 tokens to every session, about $0.0825 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code reviewDevOps and cloudTestingdappethereumhelmkubernetes
Related

Other instructions, from other repositories

openclaw-operator CLAUDE.md

Instructions for paperclipinc/openclaw-operator, covering claude.md — openclaw kubernetes operator, project overview, commands, architecture and reconciliation rules.

paperclipinc/openclaw-operator · 2,569 tokens

charts CLAUDE.md

Instructions for duyet/charts, covering claude.md - project philosophy & development guide, the vision, core principles, 1. simplicity without losing power and 2. consistency is kindness.

duyet/charts · 3,153 tokens

helm-zabbix CLAUDE.md

Instructions for zabbix-community/helm-zabbix, covering claude.md, repository overview, common commands, architecture and template/value organization.

zabbix-community/helm-zabbix · 2,065 tokens

metamask-extension AGENTS.md

AGENTS.md instructions for MetaMask/metamask-extension, covering agents.md, agent instructions summary, critical rules for agents, comprehensive guidelines location and quick setup.

MetaMask/metamask-extension · 14,674 tokens

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).

feiskyer/openclaw-kubernetes · 1,902 tokens

dakera-deploy CLAUDE.md

Claude Code instructions for Dakera-AI/dakera-deploy, covering dakera-deploy, key commands, architecture and conventions.

Dakera-AI/dakera-deploy · 296 tokens