agentmods.dev

Agent-Team CLAUDE.md

Agent-Team CLAUDE.md is an instructions file for coding agents from Tenon-Net/Agent-Team. It costs 910 tokens per session, scanned A, original, MIT.

Project instructions for maintaining the Agent-Team plugin. They explain session setup, the difference between maintaining the plugin and using it in another project, and how releases are published.

In plain words
What is it for?
Use them when changing Agent-Team skills, scripts, manifests, or release details, and when deciding which supporting instructions to read first.
Why use it?
They prevent maintainers from confusing plugin development with runtime use and from publishing changes without updating the version users receive.

Instructions file

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

not rated 2 26d ago A scan 910 tokens original MIT
View the source file Tenon-Net/Agent-Team
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/tenon-net/agent-team/claude-md
Clone the repo
git clone --depth 1 https://github.com/Tenon-Net/Agent-Team

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 Agent-Team CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tenon-net/agent-team/claude-md.svg)](https://agentmods.dev/instructions/tenon-net/agent-team/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tenon-net/agent-team/claude-md"><img src="https://agentmods.dev/badge/instructions/tenon-net/agent-team/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 910 This file is loaded in full into every session.
When invoked 910 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00910 $0.00910
Opus 5 $0.00455 $0.00455
Sonnet 5 $0.00182 $0.00182
Haiku 4.5 $0.00091 $0.00091

Measured 4d ago against content hash cf8e9bd13e33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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 · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — agent-team

Claude Code session entry for maintaining this plugin. Product map, invariants, and test gate: AGENTS.md (read that first for any non-trivial work).

Session start

  1. git status --short --branch — confirm main / clean or known WIP.
  2. Skim AGENTS.md map + invariants.
  3. For skill/loop changes: skills/agent-team/SKILL.md.
    For spawn/argv/trust: scripts/AGENTS.md then the file you touch.
    For CLI “why”: skills/agent-team/docs/CONTEXT.md.

You are editing the plugin, not running /agent-team against a product repo unless the user asks for a live probe.

Two jobs (do not confuse)

Job You are… Source of truth
Maintainer Changing this repo AGENTS.md, scripts, skill, manifests
Brain at runtime User ran /agent-team elsewhere Installed skill under CLAUDE_PLUGIN_ROOT — follow skills/agent-team/SKILL.md only

Release (user-visible publish)

Claude Code upgrades plugins when the resolved version string changes — not when Git tags move. Stale version + new commits ⇒ installed users keep the old cache.

Bump when

Intentional publish that should reach existing installs (feature, behavior fix, skill/script users execute). Hold the bump for private WIP until ready to ship.

Steps (one release commit or a tight series)

  1. Set the same semver in all three places:
    • .claude-plugin/plugin.json → version
    • .claude-plugin/marketplace.json → top-level version
    • .claude-plugin/marketplace.json → plugins[] entry agent-team → version
  2. Prepend CHANGELOG.md: ## [X.Y.Z] — YYYY-MM-DD + Added/Fixed/Changed.
  3. Sync version mentions in README.md and README.zh-CN.md if present.
  4. Commit: Release X.Y.Z: <one-line summary>.
  5. git push origin HEAD (tag optional, not required for plugin update).

Done when

  • Three version fields match
  • CHANGELOG.md has the section
  • origin/main includes the commit
  • User path still:
    /plugin marketplace update agent-team →
    /plugin update agent-team →
    /reload-plugins if skills look stale

Read the full file on GitHub · 98 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. 4d ago First seen · 98 lines · 910 tokens per session scan A cf8e9bd13e33

Subscribe to this mod's changes

Agent-Team CLAUDE.md is an instructions file published in the GitHub repository Tenon-Net/Agent-Team (2 stars, last pushed 26d ago), licensed MIT. It adds 910 tokens to every session, about $0.0046 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 agentsGit and workflowReleasesagent-teamai-agentsclaude-codecodexgrok
Related

Other instructions, from other repositories

planning-with-files AGENTS.md

AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.

OthmanAdi/planning-with-files · 2,236 tokens

OneManCompany CLAUDE.md

Instructions for 1mancompany/OneManCompany, covering gstack and skill routing.

1mancompany/OneManCompany · 365 tokens

openrouter-mcp-multimodal AGENTS.md

AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).

stabgan/openrouter-mcp-multimodal · 793 tokens

OpenMicro AGENTS.md

Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.

stephenleo/OpenMicro · 123 tokens

cyxj-groksearch CLAUDE.md

Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.

chenyuxiaojin/cyxj-groksearch · 547 tokens

ThreadShelf CLAUDE.md

Instructions for ChrystianSchutz/ThreadShelf: This project's agent guidance lives in AGENTS.md — read it.

ChrystianSchutz/ThreadShelf · 76 tokens