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 15,387 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: reads .claude/ paths; mentions CLAUDE.md; positional $N argument.

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 7d ago E scan ✓ AI review 15,387 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 15,387 This file is loaded in full into every session.
When invoked 15,387 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 $0.15387 $0.15387
Opus 5.5 $0.06155 $0.06155
Sonnet 5.5 $0.03077 $0.03077
Haiku 4.5 $0.01539 $0.01539

Measured 7d ago against content hash 1d057fa251c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 7d 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.

- **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 · 835 lines

How it starts

The opening of the file, as written. The whole thing — 835 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:

  • File edits, test runs, npm installs
  • New endpoint additions
  • Documentation updates
  • Signed local commits that pass the pre-commit gate

Claude Code deploys and pushes ratified work (founder ruling 3 Oct 2026); npm publish stays with the founder (passkey).

The founder's alone; an agent never does these, even when tests pass (Orchestration Directive v2.0, 2026-07-15, in ~/.claude/CLAUDE.md):

  • npm or PyPI publishes, payments, public posts

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 · 835 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. 7d ago Changed · +1 lines · +195 tokens per session 1d057fa251c0
  2. 10d ago Changed · -1 tokens per session 04014d065489
  3. 20d ago Changed · -35 lines · -791 tokens per session fc18ceabf7c4
  4. 21d ago Changed · +20 lines · +650 tokens per session 382133d71a04
  5. 22d ago Changed · -31 lines · -757 tokens per session 910fbed3a002
  6. 24d ago Changed · -4 lines · +133 tokens per session 3df909fefcb1
  7. 25d ago Changed · +52 lines · +1,347 tokens per session 438b505632b6
  8. 27d ago Changed · -72 lines · -1,019 tokens per session 16f292b0a241
  9. 1mo ago Changed · +55 lines · +1,275 tokens per session bb01a8961e56
  10. 1mo ago First seen · 849 lines · 14,355 tokens per session scan E 3a67833bc8bb

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 7d ago), licensed MIT. It adds 15,387 tokens to every session, about $0.0615 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 2026-08-31.

mcp-server
Related

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).

microsoft/vscode · 9,715 tokens

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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

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).

microsoft/vscode · 2,750 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 · 4,261 tokens