web3-signals-mcp: Instructions file for Codex

AGENTS.md

web3-signals-mcp AGENTS.md is an instructions file for Codex, OpenCode from manavaga/web3-signals-mcp. It costs 1,217 tokens per session, scanned A, original, MIT.

A set of AI agents that watches cryptocurrency market data and combines signals about large trades, derivatives, technical indicators, market mood, and narratives into scored market signals.

In plain words
What is it for?
Use it to monitor signals for supported crypto assets, compare bullish and bearish conditions, and review how different market factors affect a score.
Why use it?
It brings several kinds of crypto market information together and accounts for missing data and whether signals point up or down.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: positional $N argument.

This is manavaga/web3-signals-mcp's own configuration. It tells Codex and OpenCode how to work on web3-signals-mcp 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 web3-signals-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to manavaga/web3-signals-mcp. 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/manavaga/web3-signals-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/manavaga/web3-signals-mcp

Made for: Codex, OpenCode.

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 web3-signals-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/manavaga/web3-signals-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/manavaga/web3-signals-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/manavaga/web3-signals-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/manavaga/web3-signals-mcp/agents-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 web3-signals-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/manavaga/web3-signals-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/manavaga/web3-signals-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,217 This file is loaded in full into every session.
When invoked 1,217 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01217 $0.01217
Opus 5 $0.00609 $0.00609
Sonnet 5 $0.00243 $0.00243
Haiku 4.5 $0.00122 $0.00122

Measured 8d ago against content hash 616e2edc6926, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

web3-signals-mcp AGENTS.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 8d 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.

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.

AGENTS.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web3 Signals Agent

Identity

  • Name: Web3 Signals Agent
  • Description: Multi-agent crypto market intelligence system. Five specialized AI agents analyze whale activity, derivatives positioning, technical indicators, narrative momentum, and market data — fused into scored signals for 20 crypto assets with regime-aware scoring and LLM insights.
  • Version: 0.3.0
  • Provider: Web3 Signals

Architecture

Web3 Signals is a multi-agent market intelligence system that fuses 5 independent data dimensions into actionable scored signals (0-100).

Signal Generation (every 15 minutes)

  1. 5 specialized agents independently score each asset (0-100) with continuous proportional scoring — no flat buckets, indicators like RSI, funding rate, and F&G produce proportional scores across their full range
  2. Direction-aware asymmetric weighting — different weight sets for bullish vs bearish leans, based on per-dimension accuracy data
  3. Direction gating — zero out dimensions with historically bad accuracy in specific directions (e.g. whale data gated in bullish direction due to 16-27% accuracy)
  4. Dynamic data reweighting — agents with missing/partial data get reduced weight, redistributed to agents with full data
  5. Velocity overlay — computes rate-of-change of RSI, MACD, F&G, and funding rate across 1h/4h/24h windows. When indicators are accelerating against the signal (e.g. RSI still falling while system says BUY), dampens the signal by 30-70%. Prevents premature contrarian calls.
  6. Trend override — in confirmed BTC downtrends (price >5% below 30D MA), contrarian boost on market/derivatives is dampened by 30%, allowing bearish signals to emerge
  7. Dynamic abstain zone — threshold adjusts based on Fear & Greed: extreme conditions narrow the band (more signals), neutral markets widen it (fewer, better signals)

Scoring Philosophy

Contrarian / mean-reversion: Fear = buying opportunity, greed = danger. When the crowd panics, the system looks for value. When euphoria peaks, it signals caution.

Read the full file on GitHub · 88 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. 8d ago First seen · 88 lines · 1,217 tokens per session scan A 616e2edc6926

Subscribe to this mod's changes

web3-signals-mcp AGENTS.md is an instructions file published in the GitHub repository manavaga/web3-signals-mcp (3 stars, last pushed 22d ago), licensed MIT. It adds 1,217 tokens to every session, about $0.0061 per session on Opus 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.

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens