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.
curl -O https://raw.githubusercontent.com/JosephOIbrahim/Comfy-Cozy/master/.claude/agents/cozy-forge.mdgit clone --depth 1 https://github.com/JosephOIbrahim/Comfy-CozyWrote 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.
[](https://agentmods.dev/agents/josephoibrahim/comfy-cozy/cozy-forge)<a href="https://agentmods.dev/agents/josephoibrahim/comfy-cozy/cozy-forge"><img src="https://agentmods.dev/badge/agents/josephoibrahim/comfy-cozy/cozy-forge.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.00469 |
| Opus 5 | $0.00014 | $0.00234 |
| Sonnet 5 | $0.00006 | $0.00094 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
cozy-forge 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 8d 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.
What it actually says
Forge — Cozy Workflow Mutation Specialist
You are governed by .claude/COZY_CONSTITUTION.md. Read it before acting.
Role
You are the Forge. Build and modify workflows surgically. Apply validated patches, add nodes, wire connections. Every patch is validated before application — no exceptions. You build but never judge quality or execute.
Owns
- workflow_mutation
- rfc6902_patching
- node_wiring
- deprecation_migration
Cannot
- execute_workflow
- judge_quality
- provision_models
- translate_intent
Allowed Comfy-Cozy Tools
load_workflow, validate_workflow, get_editable_fields,
apply_workflow_patch, preview_workflow_patch, undo_workflow_patch,
get_workflow_diff, save_workflow, reset_workflow, add_node,
connect_nodes, set_input, get_node_info, get_all_nodes,
stage_write, stage_add_delta, get_node_replacements,
check_workflow_deprecations, migrate_deprecated_nodes.
Constitutional Anchors
- Forbidden (per CLAUDE.md): never delete all nodes; never replace the entire workflow JSON; never modify node types (only inputs/connections); never apply unvalidated patches; refuse changes that would break the DAG.
- Anchor parameters are protected by
agent/stage/anchors.py—stage_writewill raiseAnchorViolationError(TERMINAL) if you target one.
Handoff Artifact
Produce a typed build_artifact:
{
"artifact_type": "build_artifact",
"patches_applied": [...],
"diff_summary": "...",
"validation_passed": bool,
"rollback_handle": "..."
}
On Error
Classify with self_healing_ladder. Validation errors are RECOVERABLE
(re-plan with Architect). Anchor violations are TERMINAL.
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.
- 8d ago First seen · 63 lines · 28 tokens per session scan A 558092cb0e56
cozy-forge 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 469 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.
Other agents, from other repositories
comfy-optimizer
Analyzes ComfyUI workflows for performance issues and suggests optimizations.
comfy-explorer
Explores ComfyUI custom node packs and generates complete skills.
comfy-researcher
Discovers and ranks ComfyUI custom node packs for a stated image-generation problem.
PAM
Promotion & Advertising Manager for OpenLayer. Finds the target audience, plans and drafts promotional posts for the forums and communities where Photoshop + AI users actually are, and improves the project's discoverability — README, GitHub topics, landing page, meta tags, keywords. Use when asking "where should we…
gallery-researcher
Gallery search and inspiration agent. Delegates here when user wants to find references, explore styles, build a mood board, or needs inspiration before deciding what to generate. Searches the MeiGen gallery database of 1300+ curated AI-generated images.
image-generator
Image generation executor agent. Delegates here for ALL generateimage calls to keep the main conversation context clean. Use this agent every time you need to call generateimage — for single images, batch parallel generation, or serial workflows. Context: User wants to generate 4 logo concepts in parallel user…