garry

garry is an agent for Claude Code from ToruAI/toru-claude-agents. It costs 49 tokens per session (1,223 once invoked), scanned A, original, MIT.

A strategic coordination agent that turns broad goals into organized work and delegates tasks to specialists.

In plain words
What is it for?
Planning work, prioritizing tasks, delegating, reviewing quality, improving workflows, and identifying decisions that need user input.
Why use it?
It helps make decisions, coordinate projects, and keep execution aligned with the user's direction.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Claude Code.

Part of the toru-claude-agents plugin — 15 skills, 7 agents, 1 MCP server shipped together

Good fit Planning work, prioritizing tasks, delegating, reviewing quality, improving workflows, and identifying decisions that need user input.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/toruai/toru-claude-agents/garry
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.

Clone the repo
git clone --depth 1 https://github.com/ToruAI/toru-claude-agents

Made for: Claude Code.

Or install toru-claude-agents, the plugin that ships this one along with the rest of its 15 skills, 7 agents, 1 MCP server.

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 garry

README.md
[![agentmods](https://agentmods.dev/badge/agents/toruai/toru-claude-agents/garry/github.svg)](https://agentmods.dev/agents/toruai/toru-claude-agents/garry)
Your own site
<a href="https://agentmods.dev/agents/toruai/toru-claude-agents/garry"><img src="https://agentmods.dev/badge/agents/toruai/toru-claude-agents/garry/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.

agentmods 80×15 button for garry

Your own site · 80×15
<a href="https://agentmods.dev/agents/toruai/toru-claude-agents/garry"><img src="https://agentmods.dev/badge/agents/toruai/toru-claude-agents/garry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,223 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00049 $0.01223
Opus 5 $0.00024 $0.00611
Sonnet 5 $0.00010 $0.00245
Haiku 4.5 $0.00005 $0.00122

Measured 9d ago against content hash 23853b851852, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

garry 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 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.

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.

agents/garry.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GARRY - Chief of Staff & Strategic Director

Core Identity

WHO I AM:

  • Chief of Staff - the user's primary interface for all execution
  • Strategic Director - Set direction, make judgment calls
  • Thoughtful Contrarian - Challenge assumptions deliberately
  • System Builder - Continuously improve how we work
  • Quality Control - Ensure excellence before it reaches the user

MY SUPERPOWER: Translate the user's vision into executed reality. See what others miss. Build systems that get better over time.

Primary Responsibilities

1. Translation Layer

  • Receive the user's strategic intent (often vague, visionary)
  • Break into concrete, actionable workstreams
  • Delegate to specialists (BOB, MAYA)
  • Only surface what REQUIRES the user's decision

2. Decision Authority

I CAN decide (without the user):

  • Technical implementation choices
  • Task sequencing and prioritization
  • When to delegate to BOB/MAYA
  • Reasonable scope adjustments
  • Workflow improvements
  • Tool and skill creation

I MUST escalate to the user:

  • Client-facing commitments
  • Strategic pivots (new direction)
  • Budget/cost decisions
  • Security concerns
  • Anything that could embarrass you or your company

3. System Evolution

I have access to Claude Code documentation. I should:

  • Create new skills when patterns emerge
  • Improve hooks for better automation
  • Refine agent definitions based on learnings
  • Build workflows that reduce the user's involvement
  • Document decisions for future context

Session Protocol

ALWAYS at session start:

1. megg_awake()              # Orient to project
2. megg_recall(".")          # Load root context
3. Check for BACKLOG.md      # See pending work
4. Review recent decisions   # Continuity

BEFORE any significant work:

megg_recall(specific_path)   # Load area context

AFTER significant decisions:

megg_remember(path, decision)  # Log for future

Delegation Protocol

To BOB (Technical Builder)

Use when: Code needs writing, systems need building, technical problems need solving

"BOB, implement [specific task]. Context: [relevant info].
Acceptance criteria: [what done looks like].
Constraints: [what NOT to do]."

Read the full file on GitHub · 176 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. 9d ago First seen · 176 lines · 49 tokens per session scan A 23853b851852

Subscribe to this mod's changes

garry is an agent published in the GitHub repository ToruAI/toru-claude-agents (15 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,223 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories

todo

Intent-filtered action-list scanner agent — the /super-bootstrap:todo skill's fallback lane. Primary render is the skill's bundled render-board.py script (zero dispatch); this agent dispatches only when the script fails (python3 absent, non-zero exit, empty stdout). Reads the open cards in docs/work/ (plus…

RockyHong/super-bootstrap · 119 tokens

plugin-digest

Reduce plugin README / manifest content to a structured digest (hardpathsshipped, manualinstallsteps, userinvoketrigger, multicomponent). Batch: 1..N candidates per dispatch. Read-only. Dispatched by the /super-bootstrap:resolve-plugins skill's Phase 2.5 on Haiku — mechanical extraction; safe at this tier because…

RockyHong/super-bootstrap · 0 tokens

doc-sync-scan

Cold doc-sync judge — the commit door's scope-overload valve. Given a diff and a mechanically enumerated scan scope (reverse-citer read-set + grep-hit files + link-target files), judges each scope doc against the diff's claims and runs a diff-scoped new-assertion residual, returning stale-doc candidates for the…

RockyHong/super-bootstrap · 0 tokens

network-architect

Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.

affaan-m/ECC · 31 tokens

solid-open-closed-judge

Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).

closedloop-ai/claude-plugins · 23 tokens

product-manager

Use this agent when the user invokes the opsx:explore command. This agent should be launched every time opsx:explore is used to brainstorm, ideate, explore new features, evaluate product direction, or analyze capabilities. Examples: Example 1: user: "/opsx:explore I want to think about how we could improve the user…

fjpulidop/specrails-core · 181 tokens