Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/sandyup/comfyui-mcp/comparegit clone --depth 1 https://github.com/sandyup/comfyui-mcpWhat 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 | $0.00010 | $0.00885 |
| Opus 5 | $0.00005 | $0.00443 |
| Sonnet 5 | $0.00002 | $0.00177 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade A, and why
compare 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/comfy-compare — Compare Two Workflows
The user wants to see the differences between two ComfyUI workflows — what nodes were added, removed, or changed.
Instructions
-
Parse the arguments. The argument is: $ARGUMENTS
If no argument was provided, ask the user for two workflow sources.
Split the argument on
" vs "or" VS "to get two sources. Each source can be:- File path: a path to a workflow JSON file — read it with the Read tool
- Saved workflow name: a name from ComfyUI's library — load with
get_workflow last: the most recent execution — load fromget_history- Prompt ID: a specific execution ID — load from
get_historywith that ID
-
Load both workflows. Read/fetch both workflow sources. Label them Workflow A (first) and Workflow B (second).
-
Normalize to API format. If either workflow is in UI format (has
"nodes"and"links"arrays), note this and work with the node data. For consistent comparison, map both to a common structure:- Node identifier: use
class_type+ node ID - Inputs: named input keys with their values
- Node identifier: use
-
Compare the workflows. Perform a structural diff:
a. Nodes only in A: nodes present in A but not in B (matched by node ID, then by class_type if IDs differ) b. Nodes only in B: nodes present in B but not in A c. Nodes in both: matched by node ID and class_type
For matched nodes, diff the inputs:
- Changed values: same input name but different value (e.g., steps: 20 vs 30)
- Changed connections: same input name but different source node or slot
- Added inputs: input present in B but not in A
- Removed inputs: input present in A but not in B
-
Present the diff. Format the comparison clearly:
=== Workflow Comparison === Nodes only in A (removed): - Node 5: CLIPTextEncode (negative prompt encoder) Nodes only in B (added): - Node 12: UpscaleLatent Changed parameters: - Node 3 (KSampler): steps: 20 → 30 cfg: 7.0 → 8.5 sampler_name: euler → dpmpp_2m - Node 1 (CheckpointLoaderSimple): ckpt_name: sd_xl_base.safetensors → juggernaut_xl.safetensors
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.
- yesterday First seen · 84 lines · 10 tokens per session scan A d75cd6a8a47d
compare is a command published in the GitHub repository sandyup/comfyui-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 885 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.