SigRank SignalAF — AI Operator Cascade & Leaderboard

io.github.SunrisesIllNeverSeePublished by GitHub account SunrisesIllNeverSeev1.0.47Updated Oct 24, 2026

SigRank SignalAF on-device scanner — four-token cascade, leaderboard, 25 local tools.

The publisher's own server: Ephemeris Time-Series Forecasting

VerifiedSTDIODesktop onlyData & AnalyticsAI & ML

Overview

AI-generated overview

Local SigRank scanner that lets an assistant read your AI token usage, compute cascade metrics, view the public leaderboard, and optionally publish a signed, re

What you can do
Inspect local AI usage: pull token counts from supported session logs and compare across time windows and platforms, plus calculate metrics from counts you supply and fetch the standard record definition. Read public results: leaderboard, operator profiles and peer discovery. Explore possible changes: diagnose the token cascade, simulate a change and get improvement suggestions. Enroll and submit: bind a device with a connect code and publish a signed snapshot, with a dry-run option.
When to use it
Useful when you want an assistant to audit your own AI token usage (input, output, cache writes and reads), understand the Yield/Leverage/Velocity/SNR/10xDEV metrics, or compare against the public SigRank leaderboard. Publishing is optional and only needed if you want a ranked entry.
Requirements
Runs locally over stdio via npx (Node.js 20 or later); no global install needed. Publishing requires signing in at signalaf.com and creating a connect code to enroll the device. No environment variables or headers are declared.
Before you install
Publishing sends a signed payload containing the four pillars, account and device identifiers, signature, platform/version, counts and report metadata; prompt text, responses, code and file paths are stated not to be included, so inspect with a dry run first. Enrollment binds a device signing key whose private key stays local. The optional loopback proxy forwards provider-bound request content and credentials in memory and is off by default.

Installation

In SourceWeft

  1. Open SigRank SignalAF — AI Operator Cascade & Leaderboard in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

SigRank CLI & MCP

Read your local AI usage, inspect the token cascade, and optionally publish a signed snapshot to the SigRank leaderboard on SignalAF.

bash
npx sigrank

[npm] [CI] [License: MIT]

Website · Quickstart · MCP setup · Tool and adapter reference · Privacy

What it does

  • Reads usage metadata from supported local AI session logs.
  • Shows input, output, cache-write, and cache-read counts across available time windows.
  • Calculates Yield, Leverage, Velocity, SNR, and 10xDEV locally.
  • Provides a terminal dashboard and MCP tools for AI clients.
  • Submits signed telemetry only when you choose to publish.

This evaluates observable token-processing patterns, not model quality, work quality, productivity, or business outcomes. An adapter may estimate a pillar when its source does not expose it separately; those limitations are documented in the adapter reference.

Get started

Requires Node.js 20 or later. No global install is required.

Explore locally

bash
npx sigrank                       # interactive dashboard in a terminalnpx sigrank board --once          # public leaderboard, one-shotnpx sigrank board --window 7d --once

The dashboard includes Dashboard, Trends, Compare, Board, Watch, and Connect tabs. Use 1–6 or the arrow keys to switch, R to refresh, and Q to quit.

Publish your own snapshot

  1. Sign in at signalaf.com and create a connect code in Settings.
  2. Enroll this device, then inspect the dry-run payload.
  3. Submit when you are ready to publish.
bash
npx sigrank enrollnpx sigrank submit --dry-runnpx sigrank submit

Enrollment binds a device signing key to your operator account. The private key stays on your device. The server verifies and re-scores submitted telemetry; a local preview is not a guaranteed public rank.

For repeated use, an optional global installation provides the same commands:

bash
npm install -g sigranksigrank

Connect an MCP client

Add this server to your client's MCP configuration:

json
{  "mcpServers": {    "sigrank": {      "command": "npx",      "args": ["-y", "sigrank"]    }  }}

The entry point automatically runs an MCP stdio server when launched without a terminal. MCP tool names are called by the client; they are not shell commands.

TaskTools
Inspect local usagetokenpull, rank_windows, tokenpull_compare
Calculate from supplied countsrank_paste, get_sigrank_standard_record
Read public resultsget_leaderboard, get_operator, discover_peers
Explore possible changesdiagnose_cascade, simulate_change, suggest_improvements
Enroll and submitenroll, submit_verified

For the full list, arguments, and adapter paths, see the CLI and MCP reference. Publishing through submit_verified requires confirm: true; dry_run: true inspects the payload without publishing.

Command guide

CommandPurpose
sigrankOpen the terminal dashboard
sigrank board --oncePrint the public leaderboard
sigrank compare --platform codexAudit token counts across available local sources
sigrank watch --window 7dWatch local usage updates
sigrank enrollBind a device using a connect code
sigrank submit --dry-runInspect a signed submission without sending it
sigrank submitPublish a verified submission
sigrank proxyStart the optional loopback usage proxy
sigrank --helpShow the current command reference

Optional usage proxy

Some clients do not persist all provider-reported usage in their session files. sigrank proxy can capture usage from compatible Anthropic or OpenAI API traffic when a client supports a custom API base URL.

The proxy is off by default and binds only to loopback. It forwards provider-bound request/response content and credentials in memory, but does not persist their content. Its local usage log contains token counts and metadata. See the privacy contract before using it.

How measurement works

Four token pillars feed the calculation:

text
Yield (Υ) = (cache_read × output) / input²Leverage  = cache_read / inputVelocity  = output / inputSNR       = output / (input + output)10xDEV    = log₁₀(Leverage)

This package distributes the Upsilon measurement engine through the sigrank CLI/MCP compatibility command. SigRank is the public leaderboard and proof surface on SignalAF. TTEOP defines the protocol semantics; MO§ES™ is the governance framework.

The implementation delegates canonical calculations through token-cascade to tteop-spec. See the TTEOP implementation profile and protocol compatibility notes.

Privacy

Local inspection does not publish your usage. Signed submissions include the four pillars plus account/device identifiers, signature, platform/version information, counts, and report metadata. Enrollment also sends a device label.

Prompt text, response text, source code, repository contents, and local file paths are not part of the ranked submission payload. The optional proxy's transient handling of content is separate from what is persisted or submitted.

Read the full payload and privacy details, and use submit --dry-run to inspect what would be sent.

Development

bash
git clone https://github.com/SunrisesIllNeverSee/sigrank-mcp.gitcd sigrank-mcpnpm installnpm testnpm run test:packaged

Run node index.mjs in a terminal for the dashboard, or configure the checked-out entry point in an MCP client. Release versions are managed by the repository's explicit publishing workflow; a documentation commit does not publish an npm release.

Related projects

  • sigrank-app — SignalAF website, profiles, public API, and leaderboard.
  • token-cascade — measurement implementation consumed by this package.
  • TTEOP — protocol specification and semantics.

Contributing and security

See the contributing guide. Open bugs in GitHub Issues; report vulnerabilities privately through the security policy.

License

MIT.

Source: README.md at commit 871c40d

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

5
  1. v1.0.47LatestOct 16, 2026
  2. v1.0.46Oct 14, 2026
  3. v1.0.44Oct 5, 2026
  4. v1.0.43Oct 5, 2026
  5. v1.0.12Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Cascade integrations