agentmods.dev

Suber-Agent-Team: Instructions file for Claude Code

CLAUDE.md

Suber-Agent-Team CLAUDE.md is an instructions file for Claude Code from stephenpham68/Suber-Agent-Team. It costs 1,028 tokens per session, scanned A, original, MIT.

A set of instructions for a provider-neutral team of sub-agents, meaning smaller assistants that share work with a main assistant through MCP, a tool-connection standard. It describes the project structure, commands, model providers, and worker tools.

In plain words
What is it for?
Use it when working on the project's TypeScript MCP server, agent delegation, parallel task handling, research flow, provider support, retries, or worker file and web tools.
Why use it?
It gives coding assistants the project context needed to change or run the Suber-Agent-Team safely and consistently.

Instructions file for Claude Code

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

This is stephenpham68/Suber-Agent-Team's own configuration. It tells Claude Code how to work on Suber-Agent-Team 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 Suber-Agent-Team configures →

not rated 2repo 3mo ago A scan 1,028 tokens original MIT
View source ↗ stephenpham68/Suber-Agent-Team
Reuse

Borrowing it

Nothing to install: this file belongs to stephenpham68/Suber-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.

Copy the file
curl -O https://raw.githubusercontent.com/stephenpham68/Suber-Agent-Team/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/stephenpham68/Suber-Agent-Team

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 Suber-Agent-Team CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/stephenpham68/suber-agent-team/claude-md.svg)](https://agentmods.dev/instructions/stephenpham68/suber-agent-team/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/stephenpham68/suber-agent-team/claude-md"><img src="https://agentmods.dev/badge/instructions/stephenpham68/suber-agent-team/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,028 This file is loaded in full into every session.
When invoked 1,028 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 $0.01028 $0.01028
Opus 5 $0.00514 $0.00514
Sonnet 5 $0.00206 $0.00206
Haiku 4.5 $0.00103 $0.00103

Measured 7d ago against content hash c0ef9af611a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Suber-Agent-Team 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 7d 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 · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working in suber-agent-team.

What this is

A provider-agnostic sub-agent fleet exposed over MCP. It offloads many cheap-model sub-agents (Haiku / GPT-mini / any OpenAI- or Anthropic-compatible endpoint, or Orbit) so the orchestrator's premium quota stays untouched. Stdio MCP server, read-only by default.

Layout (src/)

  • index.ts — MCP entry (stdio). stdout is JSON-RPC only; all logs go to stderr. Exits cleanly when the parent closes stdin.
  • server.ts — the MCP tool surface: delegate / fanout / map_reduce / research. Deliberately small so it adds little schema to the orchestrator's context.
  • agent.ts — the fleet: runFleet / runSingle / runMapReduce / runResearch, the SYSTEM_PROMPT + LEAD_PROMPT, and plan parsing.
  • providers.ts — the per-worker tool-use loop for the anthropic and openai wire formats. Native tool_use path + text-tool fallback for proxies that ignore the tools param. Retry/backoff on 429/5xx/network.
  • tools.ts — the worker tool layer: read_file / glob / list_dir / grep / web_fetch, plus web_search (auto-enabled when a Tavily key is set) and the dangerous write_file / edit_file / bash. grep uses ripgrep when available and falls back to an in-JS scan. All FS access is jailed to workspaceRoot; bash is denylist-guarded.
  • tool-call-parse.ts — fallback parser for backends that emit tool calls as text instead of structured calls.
  • config.ts — layered config (defaults < preset < file < env), all SUBER_* overridable.
  • rate-limiter.ts — client-side RPM/RPS self-pacing, shared per base URL.

Commands

  • Build: npm run build (tsc)
  • Dev: npm run dev (bun runs src/index.ts)
  • Config doctor: node dist/index.js --check (validates config + prints the banner, does not start the server)
  • MCP inspector: npm run inspector

Read the full file on GitHub · 48 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. 7d ago First seen · 48 lines · 1,028 tokens per session scan A c0ef9af611a4

Subscribe to this mod's changes

Suber-Agent-Team CLAUDE.md is an instructions file published in the GitHub repository stephenpham68/Suber-Agent-Team (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,028 tokens to every session, about $0.0051 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.

Building agentsClaude Codeagent-orchestrationagent-teamai-agentsanthropicclaude
Related

Other instructions, from other repositories

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

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

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

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

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