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 skills/ssube/conclave/comfyui-generatenpx skills add ssube/conclave --skill comfyui-generategit clone --depth 1 https://github.com/ssube/conclaveWrote 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/skills/ssube/conclave/comfyui-generate)<a href="https://agentmods.dev/skills/ssube/conclave/comfyui-generate"><img src="https://agentmods.dev/badge/skills/ssube/conclave/comfyui-generate.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 | $0.00052 | $0.01554 |
| Opus 5 | $0.00026 | $0.00777 |
| Sonnet 5 | $0.00010 | $0.00311 |
| Haiku 4.5 | $0.00005 | $0.00155 |
Grade A, and why
comfyui-generate scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Verify ComfyUI server is running: `curl http://$COMFYUI_HOST:$COMFYUI_PORT/system_stats` How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI Generate Skill
Generate images using ComfyUI API with Flux text-to-image and Wan 2.2 image-to-video.
For detailed workflow node maps, see references/workflows.md.
Usage
Generate an image (custom workflow)
python3 {baseDir}/generate_image.py generate \
--prompt "a gothic fantasy queen in dark armor" \
--base flux \
[--lora creature_lora:0.8] \
[--size 832x1216] \
[--output /path/to/output.png]
Generate using a named workflow
python3 {baseDir}/generate_image.py generate \
--workflow flux-lora \
--prompt "a woman in a dark fantasy setting, dramatic lighting"
Named workflows are pre-built ComfyUI pipelines with model, LoRA, sampler, and all
settings already configured. Only the positive prompt text is changed. The --base,
--lora, and --size options are ignored when using a named workflow.
Image-to-video
python3 {baseDir}/generate_image.py generate \
--workflow wan22-i2v \
--prompt "She turns slowly, silk shifting with the movement" \
--image /path/to/source.png \
--output video.webm
Override workflow parameters with --set
python3 {baseDir}/generate_image.py generate \
--workflow flux-lora \
--prompt "crystal queen" \
--set '96.inputs.lora_name=my-models/my-lora.safetensors' \
--set '96.inputs.strength_model=0.8'
List available named workflows
python3 {baseDir}/generate_image.py generate --workflow help
Check queue / history
python3 {baseDir}/generate_image.py queue
python3 {baseDir}/generate_image.py history <prompt-id>
Named Workflows
| Name | Model | LoRA Slots | Purpose |
|---|---|---|---|
flux-lora |
Flux-dev fp8 | 2 (nodes 96, 200) | Primary text-to-image, natural language prompt |
wan22-i2v |
Wan 2.2 I2V (MoE) | None | Image-to-video with auto-captioning and 2x upscale |
For detailed node maps, parameter injection points, and data flow diagrams, see references/workflows.md.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 193 lines · 52 tokens per session scan A 6ba264ffe68b
comfyui-generate is a skill published in the GitHub repository ssube/conclave (2 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 1,554 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
mempalace-recall
Recall protocol for MemPalace — search the palace before answering about past work, people, projects, or prior decisions. Apply when the user asks what was decided, what happened before, who someone is, what was discussed last time, or anything that may already be filed in their memory palace; or when mempalace-recall…
triage
Triage GitHub issues by applying type, effort, priority, and area labels. Runs in an isolated context to avoid polluting the main conversation with issue details. Delegates to a specialized triage agent with label validation hooks.
docker-extend
Use when: User wants to extend Docker with custom tools, personalize the Docker environment, or set up user-specific Docker customization. Triggers: 'extend docker', 'docker-extend', 'add tools to docker', 'customize docker', 'add my tools to the container', 'personalize docker setup', 'docker user setup', 'install…
mastering-python-skill
Modern Python coaching covering language foundations through advanced production patterns. Use when asked to "write Python code", "explain Python concepts", "set up a Python project", "configure Poetry or PDM", "write pytest tests", "create a FastAPI endpoint", "run uvicorn server", "configure alembic migrations"…
st-full-workflow
Use when the user asks to run the complete end-to-end Strikethroo workflow for a work order in one shot in this repository — triggers include full workflow, end-to-end, plan and execute, do everything, run the whole strikethroo workflow. Do not use when the user wants only one stage (create a plan, generate tasks, or…