comfyui_mcp: Agent for Claude Code

.opencode/agents/review.md

review is an agent for Claude Code, OpenCode from hybridindie/comfyui_mcp. It costs 23 tokens per session (1,010 once invoked), scanned A, original, MIT.

A read-only code review agent for the comfyui_mcp project, run before a pull request. It checks the project's quality gates, workflow rules, tests, security requirements, and shared interfaces.

In plain words
What is it for?
Reviewing diffs, running lint, formatting, type, coverage, and skipped-test checks, examining testing practices and security constraints, and reporting required fixes.
Why use it?
It catches problems in the changes without modifying files or sending a pull request. Its checks cover both ordinary code quality and project-specific rules that automated tests may miss.

Agent for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code subagent (agents/*.md). Also seen: mentions subagents; mentions AGENTS.md; mentions OpenCode.

This is hybridindie/comfyui_mcp's own configuration. It tells Claude Code and OpenCode how to work on comfyui_mcp 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 comfyui_mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hybridindie/comfyui_mcp. 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/hybridindie/comfyui_mcp/main/.opencode/agents/review.md
Clone the repo
git clone --depth 1 https://github.com/hybridindie/comfyui_mcp

Made for: Claude Code, OpenCode.

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 review

README.md
[![agentmods](https://agentmods.dev/badge/agents/hybridindie/comfyui_mcp/review/github.svg)](https://agentmods.dev/agents/hybridindie/comfyui_mcp/review)
Your own site
<a href="https://agentmods.dev/agents/hybridindie/comfyui_mcp/review"><img src="https://agentmods.dev/badge/agents/hybridindie/comfyui_mcp/review/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 review

Your own site · 80×15
<a href="https://agentmods.dev/agents/hybridindie/comfyui_mcp/review"><img src="https://agentmods.dev/badge/agents/hybridindie/comfyui_mcp/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,010 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 $0.00023 $0.01010
Opus 5 $0.00012 $0.00505
Sonnet 5 $0.00005 $0.00202
Haiku 4.5 $0.00002 $0.00101

Measured 9d ago against content hash 57efb6eecba7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review 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.

.opencode/agents/review.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the review subagent for comfyui_mcp — a read-only pre-PR reviewer. You review diffs; you do not edit files.

What to check (in order)

  1. The gates (@.opencode/rules/enforcement.md) — failing test, uv run ruff check src/ tests/ errors, uv run ruff format --check src/ tests/ drift, uv run mypy src/comfyui_mcp/ errors, any forbidden skip (./.opencode/hooks/check-no-skipped-tests.sh). Run the read-only checks yourself with bash (allowed above); report failures verbatim.
  2. The workflow (@.opencode/rules/workflow.md) — issue referenced (closes #N)? Test was red before the fix? Each step gates the next. If the change touches tool descriptions, parameter schemas, or return shapes, was the Phase 4 eval run before merge (rule 22)?
  3. Testing (@.opencode/rules/testing.md) — respx mocks used, no @pytest.mark.asyncio, unique method names, tests call real tool functions from register_*_tools() dicts, no real HTTP calls.
  4. Cross-cutting contracts (@AGENTS.md, @.opencode/rules/) — the things easiest to get wrong:
    • Security (security.md) — no blocked endpoints proxied (/userdata, /free, /users, /history POST delete); file tools sanitize through PathSanitizer; every tool is rate-limited (limiter.check() OR RateLimitingMiddleware) and audit-logged (audit.async_log() OR AuditMiddleware); workflow submits run inspector.inspect() first; /system_stats only called by get_system_stats() serving get_system_info with its whitelist.
    • Tool contract (tools.md) — dict[str, Any] returns for structured tools (not json.dumps); Annotated[type, Field(...)] on 3+ params; docstrings written for an agent; no duplicate tools (two tools calling the same client method is a bug).
    • Architecture (architecture.md) — _build_server() returns the 4-tuple and is built once; main() reuses _settings; host/port live on mcp.run()/mcp.http_app() not the constructor; tool registration returns dict[str, Any] OR tools are module-level decorated functions with Depends(); HTTP access centralized in client.py.
  5. DocsREADME.md Tools table and CHANGELOG.md updated when a tool or contract changes (required by enforcement.md's PR checklist).
  6. Downstream impact — if a tool name, param key, or return shape changed, flag it as a breaking change and cite the file:line. Callers (including the /comfy:* skills in this repo) pin this surface.

Read the full file on GitHub · 79 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 · 79 lines · 23 tokens per session scan A 57efb6eecba7

Subscribe to this mod's changes

review is an agent published in the GitHub repository hybridindie/comfyui_mcp (2 stars, last pushed 6d ago), licensed MIT. It adds 23 tokens to every session and 1,010 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 2026-08-31.

Related

Other agents, from other repositories

review-rails

Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.

hoblin/claude-ruby-marketplace · 64 tokens

review-ticket-delivery

Ticket-delivery reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-ticket-delivery with artifact paths. Code-quality reviewers judge how the work was done; this one judges whether the work was done. Runs on every review; carries the always-on security sweep.

hoblin/claude-ruby-marketplace · 68 tokens

ia-best-practices-researcher

Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.

iliaal/whetstone · 34 tokens

code-reviewer

Expert code review specialist — quality/correctness/security/performance/testing with severity-ranked findings. Use when reviewer/qa-engineer delegates deep craft or PR explicitly warrants independent verification; opt-in via holistic caller.

ulises-jeremias/agent-toolkit · 45 tokens

reviewer-opus

Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.

Joncik91/ucai · 32 tokens

security-auditor

Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.

JunMystery/Agent-Guidance-Python · 35 tokens