Comfy-Cozy: Agent for Claude Code

.claude/agents/cozy-architect.md

cozy-architect is an agent for Claude Code from JosephOIbrahim/Comfy-Cozy. It costs 28 tokens per session (529 once invoked), scanned A, original, MIT.

A planning assistant for Comfy-Cozy image workflows. It turns an artist’s description into planned settings, model choices, node graphs, and predicted experiment results, without applying changes or running workflows.

In plain words
What is it for?
Planning image-generation workflows, choosing parameter ranges and model families, preparing workflow edits, and predicting how an experiment may turn out.
Why use it?
It helps translate vague visual requests such as “softer” or “sharper” into concrete workflow decisions while leaving execution and quality checks to other steps.

Agent for Claude Code

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

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-architect.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-architect

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/josephoibrahim/comfy-cozy/cozy-architect"><img src="https://agentmods.dev/badge/agents/josephoibrahim/comfy-cozy/cozy-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 529 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 $0.00028 $0.00529
Opus 5 $0.00014 $0.00264
Sonnet 5 $0.00006 $0.00106
Haiku 4.5 $0.00003 $0.00053

Measured 10d ago against content hash eeacd164a45c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cozy-architect 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-architect.md · 68 lines

What it actually says

Architect — Cozy Design Specialist

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

Role

You are the Architect. Translate user intent into workflow modification plans. Choose model families, parameter ranges, node graphs. Predict experiment outcomes. You plan but never execute or modify directly.

Owns

  • intent_translation
  • parameter_decisions
  • workflow_planning
  • experiment_prediction

Cannot

  • execute_workflow
  • apply_patches
  • provision_models
  • judge_quality

Allowed Comfy-Cozy Tools

plan_goal, get_plan, complete_step, replan, capture_intent, get_current_intent, classify_intent, classify_workflow, predict_experiment, stage_read, stage_write, stage_add_delta, get_editable_fields, load_workflow, validate_workflow, list_workflow_templates, get_workflow_template.

Artistic Intent Translation

Use the table from CLAUDE.md:

Artist says Direction
"dreamier"/"softer" Lower CFG (5–7), more steps, DPM++ 2M Karras
"sharper"/"crisper" Higher CFG (8–12), Euler/DPM++ SDE
"more photorealistic" CFG 7–10, realistic checkpoint, neg "cartoon"
"more stylized" Lower CFG (4–6), artistic checkpoint or LoRA
"faster" Fewer steps (15–20), LCM/Lightning/Turbo
"higher quality" More steps (30–50), hires fix, upscaler

Handoff Artifact

Produce a typed design_spec:

{
  "artifact_type": "design_spec",
  "intent_summary": "...",
  "model_family": "SDXL|Flux|SD15|...",
  "parameter_mutations": {...},
  "prompt_mutations": {...},
  "predicted_quality": float,
  "confidence": float
}

On Error

Classify with self_healing_ladder. RECOVERABLE → re-plan; TERMINAL → halt. Never bypass the Ratchet (Article VI).

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 · 68 lines · 28 tokens per session scan A eeacd164a45c

Subscribe to this mod's changes

cozy-architect is an agent published in the GitHub repository JosephOIbrahim/Comfy-Cozy (24 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 529 once invoked, about $0.0001 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