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.
npx agentmods add instructions/tenon-net/agent-team/agents-mdgit clone --depth 1 https://github.com/Tenon-Net/Agent-TeamWhat 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 | $0.01270 | $0.01270 |
| Opus 5 | $0.00635 | $0.00635 |
| Sonnet 5 | $0.00254 | $0.00254 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
Agent-Team 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent-Team
Purpose
Claude Code plugin that implements a single-brain multi-agent coding
pipeline: Claude plans and judges; an Executor (grok or codex)
implements tasks in git worktrees; codex reviews read-only; Claude
merges and reports. This repository is the plugin source (marketplace +
skill + harness scripts), not a sample application.
Current version: read .claude-plugin/plugin.json → version (do not
hardcode elsewhere without updating the release checklist).
Map
| Path | Role |
|---|---|
.claude-plugin/ |
Marketplace + plugin manifest (version is the upgrade signal) — see .claude-plugin/AGENTS.md |
commands/ |
Claude Code slash-command entry (/agent-team) |
skills/agent-team/ |
Orchestration skill, schemas, ADRs, Phase findings — see skills/agent-team/AGENTS.md |
scripts/ |
Headless harness: executor / reviewer / resolve — see scripts/AGENTS.md |
README.md / README.zh-CN.md |
Human install, update, usage |
CHANGELOG.md |
Release notes by semver |
CLAUDE.md |
Claude-specific maintainer workflow (release, sessions) |
LICENSE |
MIT |
Architecture (one screen)
User → /agent-team → Claude (Brain)
│
plan.md approval + state.json under target repo .agentteam/
│
per task: worktree → run-executor.mjs → run-reviewer.mjs
│
trust+gate → commit/merge → report
| Role | Who | Writable? |
|---|---|---|
| Brain | Claude in Claude Code | worktrees/commits/judgement; no silent self-review exemption |
| Executor | grok or codex (auto prefers grok) |
only its worktree (+ result dir for codex via --add-dir) |
| Reviewer | always codex |
no (--sandbox read-only) |
Roles ≠ product names. Design intent and hard-won CLI facts:
skills/agent-team/docs/CONTEXT.md and docs/adr/.
Invariants (do not violate without an ADR)
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.
- 3d ago First seen · 114 lines · 1,270 tokens per session scan A 1cff1c8667c5
Agent-Team AGENTS.md is an instructions file published in the GitHub repository Tenon-Net/Agent-Team (2 stars, last pushed 25d ago), licensed MIT. It adds 1,270 tokens to every session, about $0.0064 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.
Other instructions, from other repositories
takt AGENTS.md
Instructions for nrslib/takt, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
OneManCompany CLAUDE.md
Instructions for 1mancompany/OneManCompany, covering gstack and skill routing.
bob-plugin-ollama-translator AGENTS.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering repository guidelines, project overview, architecture & data flow, key directories and development commands.
bob-plugin-ollama-translator CLAUDE.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
neeko AGENTS.md
Instructions for tincopper/neeko, covering neeko — repository guidelines, 项目概览, 目录结构, 前端（feature-based 架构） and 后端（domain-driven 模块化架构）.
cyxj-groksearch CLAUDE.md
Instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.