TEAM_USAGE

TEAM_USAGE is an agent for Claude Code from Auriti-Labs/geo-optimizer-skill. It costs 0 tokens per session (1,405 once invoked), scanned A, original, MIT.

A guide to the agents used by the GeoReady/GEO Optimizer project and the roles each one performs. It distinguishes coordination, code-writing, testing, security, documentation, and release work.

In plain words
What is it for?
Use it to plan work across the engine, APIs, database, dashboard, WordPress connector, security review, quality checks, documentation, and releases.
Why use it?
It helps a team choose the right specialist and understand which agents may change code or must remain reviewers.

Agent for Claude Code

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 agents/auriti-labs/geo-optimizer-skill/team_usage
Clone the repo
git clone --depth 1 https://github.com/Auriti-Labs/geo-optimizer-skill

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 TEAM_USAGE

README.md
[![agentmods](https://agentmods.dev/badge/agents/auriti-labs/geo-optimizer-skill/team_usage.svg)](https://agentmods.dev/agents/auriti-labs/geo-optimizer-skill/team_usage)
Your own site
<a href="https://agentmods.dev/agents/auriti-labs/geo-optimizer-skill/team_usage"><img src="https://agentmods.dev/badge/agents/auriti-labs/geo-optimizer-skill/team_usage.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,405 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.01405
Opus 5 $0.00000 $0.00702
Sonnet 5 $0.00000 $0.00281
Haiku 4.5 $0.00000 $0.00140

Measured 5d ago against content hash 1852dde2ae64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

TEAM_USAGE 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 5d 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/agents/TEAM_USAGE.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Team Usage Guide

GeoReady / GEO Optimizer


1. Agent inventory

Agent Role Writes code? Worktree isolation Use before impl? Use after impl?
geoready-orchestrator Coordination lead No No Yes (required) Yes (synthesis)
geo-engine-architect Engine/CLI/JSON Yes Yes Yes (design) Yes (review)
geoready-platform-api Backend/API/DB Yes Yes Yes (design) Yes (review)
geoready-dashboard-ui Dashboard/frontend Yes Yes Yes (design) Yes (review)
geo-qa-verifier QA/testing No* No No Yes (required)
geo-security-privacy-reviewer Security/privacy No No Yes Yes
geo-product-docs-release Docs/copy/release Yes Yes No Yes
geo-roadmap-release-manager Versioning/release No No Yes (planning) Yes (release gate)
geo-wordpress-connector-architect WP connector arch Yes Yes Yes (spec only) Yes (review)

*geo-qa-verifier may apply minimal fixes only if explicitly instructed and fix is directly tied to a QA finding.


2. Read-only reviewers

These agents should not modify product code:

  • geoready-orchestrator
  • geo-qa-verifier
  • geo-security-privacy-reviewer
  • geo-roadmap-release-manager

3. Code-writing implementation agents

These agents may edit/write code (use worktree isolation):

  • geo-engine-architectgeo-optimizer-skill/
  • geoready-platform-apigeoready-platform/backend/
  • geoready-dashboard-uigeoready-platform/frontend/
  • geo-product-docs-release — README, CHANGELOG, docs/, copy
  • geo-wordpress-connector-architect — plugin skeleton (only if approved)

4. Agents that should run before implementation

  1. geoready-orchestrator — always first; produces plan and agent assignments
  2. geo-roadmap-release-manager — confirm SemVer impact and release scope
  3. geo-security-privacy-reviewer — identify security requirements before building
  4. geo-engine-architect — design engine API/contract before platform builds against it

Read the full file on GitHub · 147 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. 5d ago First seen · 147 lines · 0 tokens per session scan A 1852dde2ae64

Subscribe to this mod's changes

TEAM_USAGE is an agent published in the GitHub repository Auriti-Labs/geo-optimizer-skill (767 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,405 tokens. 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.