agentmods.dev

headless-oracle-v5: Instructions file for Claude Code

CLAUDE.md

headless-oracle-v5 CLAUDE.md is an instructions file for Claude Code from LembaGang/headless-oracle-v5. It costs 10,094 tokens per session, scanned E, original, MIT.

A set of project instructions for Headless Oracle V5, a Cloudflare Worker that reports whether exchanges are open and signs its answers with Ed25519 cryptography.

In plain words
What is it for?
Use it when working on the worker, its market-state responses, payments, API keys, deployments, tests, documentation, or related web frontend.
Why use it?
It gives coding agents the project’s architecture, operating defaults, and rules for changes that need explicit approval.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; positional $N argument; mentions AGENTS.md.

This is LembaGang/headless-oracle-v5's own configuration. It tells Claude Code how to work on headless-oracle-v5 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything headless-oracle-v5 configures →

not rated 0repo changed yesterday E scan ✓ AI review 10,094 tokens original MIT
View source ↗ LembaGang/headless-oracle-v5
Reuse

Borrowing it

Nothing to install: this file belongs to LembaGang/headless-oracle-v5. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/LembaGang/headless-oracle-v5/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/LembaGang/headless-oracle-v5

Made for: Claude Code.

Wrote 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.

agentmods badge for headless-oracle-v5 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lembagang/headless-oracle-v5/claude-md/github.svg)](https://agentmods.dev/instructions/lembagang/headless-oracle-v5/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lembagang/headless-oracle-v5/claude-md"><img src="https://agentmods.dev/badge/instructions/lembagang/headless-oracle-v5/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.

agentmods 80×15 button for headless-oracle-v5 CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lembagang/headless-oracle-v5/claude-md"><img src="https://agentmods.dev/badge/instructions/lembagang/headless-oracle-v5/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,094 This file is loaded in full into every session.
When invoked 10,094 The same file — it is already loaded in full.
Security scan E 3 findings. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Fable 5.1 · 7 Sept 2026 📄 Read the review
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 5.1 $0.10094 $0.10094
Opus 5 $0.05047 $0.05047
Sonnet 5 $0.02019 $0.02019
Haiku 4.5 $0.01009 $0.01009

Measured yesterday against content hash 9fe20ca91cb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade E, and why

headless-oracle-v5 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 yesterday.

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.

- **Commit signing.** Sign commits with the SSH signing key at `~/.ssh/id_ed25519_signing`. Already configured globally — no per-commit setup needed.

Recursive force deletehighDestructive command

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

- `rm -rf` operations

Makes network callslowCapability

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

- **Routing**: Worker catch-all on `headlessoracle.com/*`; API paths handled directly, HTML paths forwarded to Pages via `fetch(request)`
CLAUDE.md · 597 lines

How it starts

The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Headless Oracle V5

Headless Oracle is a Cloudflare Worker that returns Ed25519-signed market-state attestations for 28 global exchanges. It answers one question: "Is this exchange open right now?" Every response is cryptographically signed. UNKNOWN = CLOSED (fail-closed). Revenue: x402 micropayments ($0.001 USDC on Base), API keys (free 500/day, paid tiers via Paddle), free trial (3 signed receipts/day/IP).

Operational Defaults (Solo Founder Repo)

Auto-approved — no confirmation needed:

  • Auto-deploy after all tests pass
  • Push directly to main — no PR required
  • File edits, test runs, npm installs
  • Cloudflare deployments when tests pass
  • New endpoint additions
  • Documentation updates

Still requires explicit confirmation in the message:

  • git push --force
  • rm -rf operations
  • Secret rotation or credential changes
  • Anything that permanently deletes existing data

Architecture in 30 Seconds

  • Single TypeScript file: src/index.ts (~12,400 lines)
  • Runtime: Cloudflare Workers (edge, no origin server) — API only, zero HTML
  • HTML: Served by Cloudflare Pages via headless-oracle-web repo
  • Routing: Worker catch-all on headlessoracle.com/*; API paths handled directly, HTML paths forwarded to Pages via fetch(request)
  • KV namespaces: ORACLE_TELEMETRY (metrics/usage), ORACLE_API_KEYS (auth + billing state), ORACLE_OVERRIDES (manual halt overrides)
  • Signing: Ed25519 via @noble/ed25519 with CryptoKey cached in module scope
  • MCP server: POST /mcp (protocol 2024-11-05, streamable HTTP, 5 tools)
  • Payments: x402 via Coinbase CDP facilitator on Base mainnet
  • Billing: Paddle (subscriptions + credit packs), keys stored in Supabase + KV cache
  • Conversion: /v5/keys/instant instant key provisioning, enhanced 402/429 with agent_upgrade_paths, funnel telemetry
  • Email: Resend for key delivery
  • Durable Objects: StreamCoordinator (SSE), WebhookDispatcher (state-change fan-out)
  • OpenAPI: 78 paths in /openapi.json (11 semantic tags, 2 server URLs, MIT license)
  • SDKs: packages/sdk-typescript/ (@headlessoracle/sdk), packages/sdk-python/ (headless-oracle-sdk) — not yet published
  • Published packages: headless-oracle-mcp (npm), headless-oracle (PyPI), framework SDKs (LangChain, CrewAI, Strands)

Read the full file on GitHub · 597 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. yesterday Changed · +278 lines · +1,733 tokens per session 9fe20ca91cb1
  2. 9d ago First seen · 319 lines · 8,361 tokens per session scan E bbaad101520a

Subscribe to this mod's changes

headless-oracle-v5 CLAUDE.md is an instructions file published in the GitHub repository LembaGang/headless-oracle-v5 (0 stars, last pushed yesterday), licensed MIT. It adds 10,094 tokens to every session, about $0.0505 per session on Opus 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 2026-08-31.

mcp-server
Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens