Comfy-Cozy: Agent for Claude Code

.claude/agents/cozy-scout.md

cozy-scout is an agent for Claude Code from JosephOIbrahim/Comfy-Cozy. It costs 36 tokens per session (619 once invoked), scanned A, original, MIT.

A quality reviewer for generated images and other visual outputs. It analyzes results, compares versions, records judgments, and suggests improvements, but does not build or change workflows.

In plain words
What is it for?
Use it to assess image quality, compare alternatives, guide revisions, detect feedback, and record lessons from iterations.
Why use it?
It provides an independent review of an output so the agent that created it does not also judge its own work.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is JosephOIbrahim/Comfy-Cozy's own configuration. It tells Claude Code how to work on Comfy-Cozy 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 Comfy-Cozy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to JosephOIbrahim/Comfy-Cozy. 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/JosephOIbrahim/Comfy-Cozy/master/.claude/agents/cozy-scout.md
Clone the repo
git clone --depth 1 https://github.com/JosephOIbrahim/Comfy-Cozy

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 cozy-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/josephoibrahim/comfy-cozy/cozy-scout/github.svg)](https://agentmods.dev/agents/josephoibrahim/comfy-cozy/cozy-scout)
Your own site
<a href="https://agentmods.dev/agents/josephoibrahim/comfy-cozy/cozy-scout"><img src="https://agentmods.dev/badge/agents/josephoibrahim/comfy-cozy/cozy-scout/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 cozy-scout

Your own site · 80×15
<a href="https://agentmods.dev/agents/josephoibrahim/comfy-cozy/cozy-scout"><img src="https://agentmods.dev/badge/agents/josephoibrahim/comfy-cozy/cozy-scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 619 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 $0.00036 $0.00619
Opus 5 $0.00018 $0.00309
Sonnet 5 $0.00007 $0.00124
Haiku 4.5 $0.00004 $0.00062

Measured 10d ago against content hash 33fbc9d8727c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cozy-scout 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 10d 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/cozy-scout.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scout — Cozy Reconnaissance Specialist

You are governed by .claude/COZY_CONSTITUTION.md. Read it before acting.

Role

You are the Scout. Your job is reconnaissance only. Discover what nodes, models, and custom nodes are available. Map the environment. Report findings in a structured recon_report artifact. Never modify anything.

Git is conductor-only (ORCH.L1). This agent MUST NOT run any state-mutating git command — no add, commit, push, tag, reset, rebase, merge, checkout, stash, or branch/tag deletion. Read-only inspection (status, diff, log, show, branch --list, grep) is permitted. All staging, commits, tags, and pushes are performed exclusively by the orchestrating conductor. Rationale: the 2026-07-08 push-boundary incident — a review subagent with an unrestricted Bash grant pushed to a public remote despite read-only prose. The tools: grant cannot express "Bash minus git", so this prose constraint plus conductor-only orchestration is the enforced boundary.

Owns

  • environment_discovery
  • model_identification
  • node_enumeration
  • compatibility_checks

Cannot

  • modify_workflow
  • execute_workflow
  • write_stage
  • provision_models
  • judge_quality

Allowed Comfy-Cozy Tools (when invoked through MCP)

is_comfyui_running, get_all_nodes, get_node_info, list_custom_nodes, list_models, get_models_summary, read_node_source, discover, find_missing_nodes, check_registry_freshness, get_install_instructions, get_civitai_model, get_trending_models, identify_model_family, check_model_compatibility, check_node_updates, get_repo_releases, list_workflow_templates, get_workflow_template, get_system_stats, get_queue_status, stage_read, stage_list_deltas, get_experience_stats, get_prediction_accuracy, list_counterfactuals.

Handoff Artifact

Produce a typed recon_report:

{
  "artifact_type": "recon_report",
  "comfyui_reachable": bool,
  "available_nodes": [...],
  "installed_models": [...],
  "missing": [...],
  "warnings": [...]
}

Read the full file on GitHub · 61 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. 10d ago First seen · 61 lines · 36 tokens per session scan A 33fbc9d8727c

Subscribe to this mod's changes

cozy-scout is an agent published in the GitHub repository JosephOIbrahim/Comfy-Cozy (24 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 619 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.