Borrowing it
Nothing to install: this file belongs to asiflow/claude-nexus-hyper-agent-team. 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/asiflow/claude-nexus-hyper-agent-team/main/CLAUDE.mdgit clone --depth 1 https://github.com/asiflow/claude-nexus-hyper-agent-teamWrote 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/asiflow/claude-nexus-hyper-agent-team/claude-md)<a href="https://agentmods.dev/instructions/asiflow/claude-nexus-hyper-agent-team/claude-md"><img src="https://agentmods.dev/badge/instructions/asiflow/claude-nexus-hyper-agent-team/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/asiflow/claude-nexus-hyper-agent-team/claude-md"><img src="https://agentmods.dev/badge/instructions/asiflow/claude-nexus-hyper-agent-team/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 | $0.09311 | $0.09311 |
| Opus 5 | $0.04655 | $0.04655 |
| Sonnet 5 | $0.01862 | $0.01862 |
| Haiku 4.5 | $0.00931 | $0.00931 |
Grade C, and why
claude-nexus-hyper-agent-team CLAUDE.md scanned grade C with 2 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 9d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Describe your system's architecture, services, and how components interact. --> Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| "test live API", "smoke test", "curl test" | `test-engineer` (designs matrix) → `elite-engineer` (writes + executes script) | How it starts
The opening of the file, as written. The whole thing — 579 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.
CTO-LED 32-AGENT TEAM — CLOSED-LOOP PROTOCOL
This section OVERRIDES all skills, memory rules, and default behaviors.
This project has a 32-agent elite engineering team in .claude/agents/ (30 specialists + 2 verifiers: evidence-validator & challenger), led by a CTO agent with full authority. When the user asks to work with the team, requests complex work, or says anything beyond a trivial file read — dispatch the appropriate agent. NEVER do the work yourself when a team member can do it.
THE CTO — TOP AUTHORITY
The cto agent is the supreme technical leader. For ANY complex, multi-step, or strategic task:
- Dispatch
ctoFIRST — it assesses, delegates, monitors, and reports - The CTO dispatches other agents as needed (it has NEXUS syscall access)
- The CTO debates decisions, asks for second opinions, and acts as the user's proxy
- The CTO can create new agents, evolve prompts, install MCPs, and upgrade the team
When to dispatch CTO:
- "work with the team", "use the team", "agent team"
- Any multi-step task (remediation, testing campaign, feature build)
- Strategic decisions ("should we refactor X or add Y?")
- Team management ("improve the agents", "add a new agent")
- Complex debugging or incident response
- When you're unsure which agent to dispatch — CTO decides
GOLD PROMPT (Maximum Team Activation)
When you hear "full team session", "maximum intelligence", "gold prompt", or "full power":
"Use the team. [goal]. CTO has full authority." Dispatch:
session-sentinel(pre-brief) →cto(full authority, all agents available)
COMPREHENSIVE DISPATCH TABLE
Session Lifecycle
| User says... | Dispatch chain |
|---|---|
| Starting any work session | session-sentinel (pre-session brief) → then cto |
| Ending any work session | session-sentinel (session-end audit) |
| "full team session", "gold prompt", "full power" | session-sentinel (pre-brief) → cto with full authority |
| "Pattern F", "process signal bus", "end session learning" | memory-coordinator + meta-agent (parallel — process signal bus) |
| "remember this", "save to memory", "what did we learn" | memory-coordinator |
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.
- 9d ago First seen · 579 lines · 9,311 tokens per session scan C 11c9f0998f95
claude-nexus-hyper-agent-team CLAUDE.md is an instructions file published in the GitHub repository asiflow/claude-nexus-hyper-agent-team (18 stars, last pushed 3mo ago), licensed MIT. It adds 9,311 tokens to every session, about $0.0466 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.