Borrowing it
Nothing to install: this file belongs to urantia-hub/urantia-dev-api. 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/urantia-hub/urantia-dev-api/main/CLAUDE.mdgit clone --depth 1 https://github.com/urantia-hub/urantia-dev-apiWrote 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/urantia-hub/urantia-dev-api/claude-md)<a href="https://agentmods.dev/instructions/urantia-hub/urantia-dev-api/claude-md"><img src="https://agentmods.dev/badge/instructions/urantia-hub/urantia-dev-api/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/urantia-hub/urantia-dev-api/claude-md"><img src="https://agentmods.dev/badge/instructions/urantia-hub/urantia-dev-api/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 | $0.12724 | $0.12724 |
| Opus 5.5 | $0.05090 | $0.05090 |
| Sonnet 5.5 | $0.02545 | $0.02545 |
| Haiku 4.5 | $0.01272 | $0.01272 |
Grade A, and why
urantia-dev-api 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 today.
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 — 642 lines — stays where its author put it; the contents beside it link to each section on GitHub.
urantia-dev-api
AI/developer-first API for the Urantia Papers — the hub product's backend service.
Scope of this service
This service owns Papers content (text, paragraphs, entities, search,
audio) and the hub product's per-user data (bookmarks, notes, reading
progress, preferences). It also hosts the shared OAuth infrastructure
(/auth/* — app registry, auth codes, token exchange) because that was
the natural first home for it.
This is NOT a catch-all backend for every Urantia app. Other product apps get their own services with their own databases:
urantia-listen-api/— Listen app (audio transcripts, semantic hits, streaming insights)- future product apps — same pattern
All backends validate tokens issued by accounts.urantiahub.com, but each
owns its own schema, migrations, deploy, secrets, and data retention
rules. Don't bolt new product features onto this repo just because the
auth middleware is already wired up — stand up a new service.
Tech Stack
- Runtime: Bun
- Framework: Hono + @hono/zod-openapi
- ORM: Drizzle
- Database: Supabase (Postgres + pgvector)
- Validation: Zod v4
- Linting: Biome
Dependency and toolchain pins
bun.lockis the ONLY lockfile. A stale leftoveryarn.locksat here until 2026-08-19 and kept 51 Dependabot alerts open after the real deps were fixed — GitHub scans every lockfile it finds. Never add a second one.wranglerpinned exact4.73.0— 4.124+ requires Node 22 and this machine runs Node 20. Bumping it breaksbun run deploylocally.@biomejs/biomepinned exact2.4.7— 2.5.x changes formatting rules and flags untouched files. Bump it only together with a deliberate repo-widebun run format.overrides.yamlforces the patched transitiveyamlversion.- Known baseline (pre-existing, not regressions): 223 typecheck errors and 43
Biome lint errors, measured 2026-09-18 on a clean
main. Most typecheck errors are Hono handler return-type mismatches insrc/routes/*.tsplusunknownbody types in the test files. Compare counts against this baseline before blaming a change.
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.
- today Changed · +17 lines · +428 tokens per session 0da1986ad10d
- yesterday Changed · +7 lines · +183 tokens per session 2ec517419da8
- 6d ago Changed · +1 lines · +75 tokens per session 3e6826d3721d
- 7d ago Changed · +58 lines · +1,676 tokens per session 339950755311
- 10d ago Changed · +22 lines · +450 tokens per session bb74acbb359c
- 13d ago Changed · +9 lines · +165 tokens per session c3b0823baf5b
- 14d ago Changed · +26 lines · +649 tokens per session eedf033aa7fa
- 16d ago Changed · +35 lines · +1,842 tokens per session b7fc441e3472
- 17d ago Changed · +31 lines · +459 tokens per session 99378e71f376
- 18d ago First seen · 436 lines · 6,797 tokens per session scan A 3a48efb55359
urantia-dev-api CLAUDE.md is an instructions file published in the GitHub repository urantia-hub/urantia-dev-api (1 stars, last pushed today), licensed MIT. It adds 12,724 tokens to every session, about $0.0509 per session on Opus 5.5. 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 2026-08-31.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.