Borrowing it
Nothing to install: this file belongs to ObolNetwork/obol-stack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ObolNetwork/obol-stack/main/CLAUDE.mdgit clone --depth 1 https://github.com/ObolNetwork/obol-stackWrote 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/obolnetwork/obol-stack/claude-md)<a href="https://agentmods.dev/instructions/obolnetwork/obol-stack/claude-md"><img src="https://agentmods.dev/badge/instructions/obolnetwork/obol-stack/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/obolnetwork/obol-stack/claude-md"><img src="https://agentmods.dev/badge/instructions/obolnetwork/obol-stack/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.22500 | $0.22500 |
| Opus 5.5 | $0.09000 | $0.09000 |
| Sonnet 5.5 | $0.04500 | $0.04500 |
| Haiku 4.5 | $0.02250 | $0.02250 |
Grade E, and why
obol-stack CLAUDE.md scanned grade E with 3 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 12d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- **Passthrough** (`internal/passthrough`, `cmd/obol/passthrough.go`): `obol kubectl|helm|helmfile|k9s` pass argv verbatim (exactly one leading `--` stripped). Env policy: the `obol` prefix means "target the stack": `KUB 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`. How it starts
The opening of the file, as written. The whole thing — 537 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 + 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 generatedWhat's Changed,New Contributors, andFull Changelogsections 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/stack/ ./internal/x402/ ./internal/agentcrd/
# Reuse worktree cluster: export OBOL_CONFIG_DIR=<worktree>/.workspace/config
# The paid commerce loop is covered by the release-gate flows (11/13/14), not Go tests.
# 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)
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.
- 12d ago Changed · -1 lines · +1,655 tokens per session 58b09c06f1c7
- 13d ago Changed · -18 lines · +1,546 tokens per session 300e8d6f02d5
- 20d ago Changed · +29 lines · +2,346 tokens per session scan C → E ee6c3c054e8a
- 21d ago Changed · +3 lines · +445 tokens per session 9a6eadca77bc
- 1mo ago First seen · 524 lines · 16,508 tokens per session scan C d09cb6f0a357
obol-stack CLAUDE.md is an instructions file published in the GitHub repository ObolNetwork/obol-stack (11 stars, last pushed today), licensed Apache-2.0. It adds 22,500 tokens to every session, about $0.0900 per session on Opus 5.5. A static security scan graded it E with 3 findings (reaches for credential files, 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
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
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, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.