10router CLAUDE.md

10router CLAUDE.md is an instructions file for coding agents from techysy/10router. It costs 2,391 tokens per session, scanned A, original, MIT.

Repository instructions for 10Router, a local gateway and dashboard that routes AI requests between different providers and model accounts.

In plain words
What is it for?
Setting up, running, understanding, and modifying the 10Router gateway, dashboard, routing engine, CLI launcher, and tests.
Why use it?
They explain the project's layout, request flow, commands, and separate published packages so development work follows the repository's design.

Instructions file

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/techysy/10router/claude-md
Clone the repo
git clone --depth 1 https://github.com/techysy/10router

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 10router CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/techysy/10router/claude-md.svg)](https://agentmods.dev/instructions/techysy/10router/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/techysy/10router/claude-md"><img src="https://agentmods.dev/badge/instructions/techysy/10router/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,391 This file is loaded in full into every session.
When invoked 2,391 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02391 $0.02391
Opus 5 $0.01196 $0.01196
Sonnet 5 $0.00478 $0.00478
Haiku 4.5 $0.00239 $0.00239

Measured 3d ago against content hash 987edd47f43b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

10router CLAUDE.md scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

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

- **Upstream features are re-implemented, never merged.** This fork's git history is deliberately rewritten (only techysy/ShiYanG Yu commits) and the contributor set is clean — that property is load-bearing. When upstrea
CLAUDE.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

10Router (10router-app) — a local AI routing gateway + Next.js dashboard. It exposes one OpenAI-compatible endpoint (/v1/*) and routes traffic across 40+ upstream providers with format translation, model-combo fallback, multi-account fallback, OAuth/API-key credential management, token refresh, quota/usage tracking, and optional cloud sync.

Two published artifacts live in this one repo:

  • The dashboard + gateway (root package.json, 10router-app) — the Next.js server that does the actual routing.
  • The CLI launcher (cli/, published to npm as @techysy/10router) — a separate package that installs/starts the server and manages the tray. It has its own package.json, version, and build.

The code lives in src/ (Next.js app + dashboard/compat APIs), open-sse/ (the provider-agnostic routing/translation engine), cli/ (the launcher package), and tests/.

Commands

Dashboard/gateway (run from repo root):

cp .env.example .env
npm install
PORT=20128 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run dev   # dev (webpack, port 20127 by default via next dev)
npm run build && PORT=20128 HOSTNAME=0.0.0.0 npm run start           # production
  • Bun variants: npm run dev:bun / build:bun / start:bun.
  • Default runtime port is 20128 (dashboard at /dashboard, API at /v1).
  • Lint: npx eslint . (config eslint.config.mjs, extends eslint-config-next).

CLI package (cli/):

npm run cli:pack       # build + npm pack from root
cd cli && npm run dev  # nodemon watch

Tests (vitest, in tests/, an independent ESM package — not wired into root npm test):

npm install                             # ROOT deps first — tests import from src/ which needs `open`, `undici`, etc.
cd tests && npm install                 # then tests' own deps (vitest) → tests/node_modules (allowed by tests/.gitignore)
npx vitest run                          # all tests; auto-discovers tests/vitest.config.js
npx vitest run unit/capabilities.test.js   # single file (path relative to tests/)

The committed tests/package.json test script hardcodes Unix paths (NODE_PATH=/tmp/node_modules …) — a shared-install workaround from upstream. On Windows (or anywhere), ignore it and use the npx vitest form above; vitest.config.js resolves the open-sse/@/ aliases from the repo root regardless of where vitest lives.

The suite is NOT expected to be all-green on a plain checkout. ~1872 pass, ~41 fail. Judge regressions with tests/__baseline__/verify-no-regression.mjs <results.json>, not a raw run — it passes as long as nothing that passed in the baseline now fails. Produce the report with npx vitest run --reporter=json --outputFile=…. Expected red:

  • All 41 catalogued in tests/__baseline__/known-fails.txt (golden snapshot drift, windsurf URL, network-dependent fetches, db-concurrent, …). Re-baseline deliberately with node tests/__baseline__/snapshot-known-fails.mjs <results.json> — it marks every failure in that report as expected, so read the gate output first.
  • unit/embeddings.cloud.test.js imports cloud/src/handlers/embeddings.js — the cloud/ worker dir is not in this repo, so it always fails here.
  • unit/db-benchmark.test.js imports lowdb, the DB layer that SQLite replaced — it is no longer a dependency.
  • real/*.real.test.js make live provider calls — need credentials, skip otherwise.

Suite-level failures (numFailedTestSuites) are counted separately from assertion failures: a file whose cases all pass can still fail on import or teardown. Check both.

Four files (auth/saml, unit/kimchi*, unit/cli-build-artifacts) are written against node:test, not vitest. They carry a shim that prefers vitest when importable and falls back to node:test; without it vitest reports "No test suite found" and their results silently reach no count. Copy that shim in any new node:test file.

  • *.real.test.js under tests/translator/real/ make live provider calls — skip unless credentials are set.
  • Regression baselines: tests/__baseline__/verify-*.mjs compare against committed snapshots (providers, aliases, OAuth URLs). Run these after touching provider registry / alias logic.
  • CI runs the suite on every push to main and every PR (.github/workflows/test.yml, ubuntu + Node 24, matching .nvmrc). It runs the three registry baselines, then the regression gate, and uploads the JSON report as an artifact — download that to re-baseline. The other three workflows only build (fpk / standalone / Docker).

Read the full file on GitHub · 98 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. 3d ago First seen · 98 lines · 2,391 tokens per session scan A 987edd47f43b

Subscribe to this mod's changes

10router CLAUDE.md is an instructions file published in the GitHub repository techysy/10router (11 stars, last pushed 4d ago), licensed MIT. It adds 2,391 tokens to every session, about $0.0120 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.