zypher-agent: Instructions file for Claude Code

CLAUDE.md

zypher-agent CLAUDE.md is an instructions file for Claude Code from corespeed-io/zypher-agent. It costs 856 tokens per session, scanned A, original, Apache-2.0.

A CLAUDE.md development guide for Zypher Agent, a TypeScript software development kit for building AI agents. The project is a monorepo, meaning several related packages are kept in one repository.

In plain words
What is it for?
Running the CLI, tests, formatting, linting, type checks, and understanding the core agent package, CLI package, and examples.
Why use it?
It gives Claude Code the commands, code-quality checks, and project layout needed to make changes safely across the SDK and command-line tool.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is corespeed-io/zypher-agent's own configuration. It tells Claude Code how to work on zypher-agent 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 zypher-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to corespeed-io/zypher-agent. 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/corespeed-io/zypher-agent/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/corespeed-io/zypher-agent

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 zypher-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/corespeed-io/zypher-agent/claude-md/github.svg)](https://agentmods.dev/instructions/corespeed-io/zypher-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/corespeed-io/zypher-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/corespeed-io/zypher-agent/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 zypher-agent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/corespeed-io/zypher-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/corespeed-io/zypher-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 856 This file is loaded in full into every session.
When invoked 856 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 $0.00856 $0.00856
Opus 5.5 $0.00342 $0.00342
Sonnet 5.5 $0.00171 $0.00171
Haiku 4.5 $0.00086 $0.00086

Measured 2mo ago against content hash 36293a9ec793, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zypher-agent 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 2mo 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.

CLAUDE.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 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.

Development Commands

Root workspace commands (run from repo root):

  • Run CLI: deno task cli - Runs the CLI from packages/cli
  • Test all: deno task test - Runs all tests with leak tracing
  • Test watch: deno task test:watch - Runs tests in watch mode
  • Check all: deno task checkall - Runs format, lint, and type check

Code quality

  • Type check: deno check .
  • Lint: deno lint
  • Format: deno fmt

Architecture Overview

Zypher Agent is a TypeScript SDK for building production-ready AI agents. Published as @zypher/agent on JSR.

Monorepo Structure

packages/
├── agent/          # Core SDK (@zypher/agent)
│   ├── src/        # Source code
│   └── tests/      # Tests
├── cli/            # CLI tool (@zypher/cli)
examples/
└── ptc/            # Programmatic Tool Calling example

Core Components (packages/agent/src/)

  • ZypherAgent.ts: Main agent class with reactive task execution loop. Uses RxJS Observable to stream TaskEvents. Manages message history, checkpoints, and coordinates with McpServerManager and LoopInterceptorManager.

  • factory.ts: createZypherAgent() - simplified factory that creates context, registers tools, and connects MCP servers in one call.

  • llm/: Model provider abstraction (ModelProvider interface) with implementations for Anthropic and OpenAI. Handles streaming chat completions and token usage tracking.

  • loopInterceptors/: Chain of responsibility pattern for post-inference processing. Each interceptor can return LoopDecision.CONTINUE to continue the agent loop or LoopDecision.COMPLETE to finish.

    • ToolExecutionInterceptor: Executes tool calls from LLM responses
    • MaxTokensInterceptor: Auto-continues when response hits token limit
    • ErrorDetectionInterceptor: Detects errors and prompts for fixes
  • mcp/: Model Context Protocol integration

    • McpServerManager: Manages MCP server lifecycle, tool registration, and tool execution with optional approval handlers
    • McpClient: Individual server connection with status observable
    • Supports CoreSpeed MCP Store registry for server discovery

Read the full file on GitHub · 94 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. 2mo ago First seen · 94 lines · 856 tokens per session scan A 36293a9ec793

Subscribe to this mod's changes

zypher-agent CLAUDE.md is an instructions file published in the GitHub repository corespeed-io/zypher-agent (331 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 856 tokens to every session, about $0.0034 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 2026-08-30.

Related

zypher-agent CLAUDE.md compared with instructions from other repositories

zypher-agent CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
zypher-agent CLAUDE.mdcorespeed-io/zypher-agentInstructions file3313mo agoApache-2.0A856Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode