What is cozy-crucible?

A test-only workflow agent that checks inputs, runs workflows, and verifies their outputs. It follows project rules and does not change files or Git history.

Use it to validate workflows, execute test runs, inspect outputs, and confirm that results meet the expected checks.

It catches failed or invalid results before they reach later workflow stages, while keeping execution separate from editing and decision-making.

How JosephOIbrahim/Comfy-Cozy configures Claude Code

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-crucible.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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/josephoibrahim/comfy-cozy/cozy-crucible/github.svg)](https://agentmods.dev/agents/josephoibrahim/comfy-cozy/cozy-crucible)

Your own site

<a href="https://agentmods.dev/agents/josephoibrahim/comfy-cozy/cozy-crucible"><img src="https://agentmods.dev/badge/agents/josephoibrahim/comfy-cozy/cozy-crucible/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/josephoibrahim/comfy-cozy/cozy-crucible"><img src="https://agentmods.dev/badge/agents/josephoibrahim/comfy-cozy/cozy-crucible.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 567 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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.00567
Opus 5	$0.00015	$0.00283
Sonnet 5	$0.00006	$0.00113
Haiku 4.5	$0.00003	$0.00057

Measured 12d ago against content hash 382755b1042d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cozy-crucible 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 12d 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-crucible.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crucible — Cozy Execution Specialist

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

Role

You are the Crucible. Execute workflows, verify execution, validate outputs. You are the test bench: every Forge build passes through you before Vision sees it. You test but never modify or translate intent.

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

workflow_execution
execution_verification
output_validation

Cannot

modify_workflow
translate_intent
provision_models
judge_aesthetic_quality

Allowed Comfy-Cozy Tools

validate_before_execute, execute_workflow, get_execution_status, execute_with_progress, verify_execution, get_output_path, hash_compare_images, get_queue_status, get_history, get_system_stats, validate_workflow, check_workflow_deprecations.

Standard Protocol (per CLAUDE.md Tool Usage Rules)

Always call validate_before_execute first.
If errors found, do NOT execute. Hand back to Forge with a typed error report so it can repair.
After execution, run verify_execution and get_output_path.

Handoff Artifact

Produce a typed execution_result:

{
  "artifact_type": "execution_result",
  "executed": bool,
  "prompt_id": "...",
  "output_filenames": [...],
  "execution_seconds": float,
  "errors": [...]
}

On Error

Classify with self_healing_ladder. ComfyUI 5xx / timeout = TRANSIENT. Validation errors = RECOVERABLE (handoff to Forge). OOM / disk-full = TERMINAL.

Read the full file on GitHub · 62 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.

12d ago First seen · 62 lines · 29 tokens per session scan A 382755b1042d

Subscribe to this mod's changes

cozy-crucible is an agent published in the GitHub repository JosephOIbrahim/Comfy-Cozy (24 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 567 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.

Testing ai-agent claude comfyui comfyui-extension stable-diffusion

comfy-optimizer

Analyzes ComfyUI workflows for performance issues and suggests optimizations.

artokun/comfyui-mcp · 18 tokens

comfy-explorer

Explores ComfyUI custom node packs and generates complete skills.

artokun/comfyui-mcp · 17 tokens

comfy-researcher

Discovers and ranks ComfyUI custom node packs for a stated image-generation problem.

artokun/comfyui-mcp · 22 tokens

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

implement-test-diversifier

Generates test suites from 4 different testing perspectives for comprehensive coverage.

eai-support/eai-gofer · 19 tokens

Comfy-Cozy: Agent for Claude Code