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 skills add MCKRUZ/ComfyUI-Expert --skill project-managergit clone --depth 1 https://github.com/MCKRUZ/ComfyUI-ExpertWrote 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/mckruz/comfyui-expert/project-manager)<a href="https://agentmods.dev/skills/mckruz/comfyui-expert/project-manager"><img src="https://agentmods.dev/badge/skills/mckruz/comfyui-expert/project-manager/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.
<a href="https://agentmods.dev/skills/mckruz/comfyui-expert/project-manager"><img src="https://agentmods.dev/badge/skills/mckruz/comfyui-expert/project-manager.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.00807 |
| Opus 5.5 | $0.00014 | $0.00323 |
| Sonnet 5.5 | $0.00007 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
project-manager 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Manager
Manages the lifecycle of video production projects. Each project gets a manifest, character profiles, workflow records, and asset tracking.
Project Structure
projects/{project-name}/
manifest.yaml # Project metadata, settings, status
characters/
{name}/
profile.yaml # Character description, reference images, voice profile
references/ # Source images for this character
outputs/ # Generated outputs
workflows/ # Saved ComfyUI workflow JSONs
assets/ # External assets (audio, video, images)
notes.md # Production notes, what worked/didn't
Commands
Create New Project
When user wants to start a new project:
- Ask for project name and brief description
- Create directory structure under
projects/ - Generate
manifest.yaml:
name: "{project-name}"
description: "{description}"
created: "{ISO date}"
updated: "{ISO date}"
status: active # active | paused | completed | archived
hardware:
gpu: "RTX 5090"
vram: 32
defaults:
checkpoint: "" # Filled after first successful generation
upscaler: ""
cfg: null
sampler: ""
scheduler: ""
characters: [] # List of character names
workflows: [] # List of saved workflow files
notes: ""
Create Character Profile
When user describes a character:
- Create
projects/{project}/characters/{name}/profile.yaml:
name: "{character-name}"
trigger_word: "{unique_trigger}" # e.g., "sage_character"
created: "{ISO date}"
appearance:
gender: ""
age_range: ""
ethnicity: ""
hair: ""
eyes: ""
skin: ""
build: ""
distinguishing_features: []
personality:
traits: []
voice_description: ""
reference_images:
source_type: "" # 3d_render | photograph | illustration | generated
count: 0
path: "references/"
lora:
trained: false
model_file: ""
trigger_word: ""
best_strength: null
voice:
cloned: false
model: "" # chatterbox | f5-tts | elevenlabs | rvc
sample_file: ""
settings: {}
generation_history:
preferred_method: "" # instantid | pulid | infiniteyou | kontext | lora
best_settings:
cfg: null
steps: null
sampler: ""
ip_adapter_weight: null
instantid_weight: null
successful_prompts: []
failed_approaches: []
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.
- 1mo ago First seen · 139 lines · 35 tokens per session scan A bf0fc8a23f9b
project-manager is a skill published in the GitHub repository MCKRUZ/ComfyUI-Expert (92 stars, last pushed 7mo ago), licensed MIT. It adds 35 tokens to every session and 807 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
manage-storyboard-projects
Create, find, inspect, update, or delete Codex Storyboard projects directly through MCP. Use when the user asks Codex to write a new video script or storyboard into the local storyboard app, add or revise shots, rename a project, change its aspect ratio, find an existing project, or delete one without browser…
feature-planning
Use when the user says "plan a feature", "brainstorm", "explore this idea", or wants to go from idea to structured plan and roadmap.
estimate-ticket
Estimate a Jira/Linear ticket — 'estimate PROJ-123', 'wie groß ist das?', 'should we split this?' — size + risk + split + uncertainty, sibling of /refine-ticket, close-prompt.
module-detect-on-the-fly
When editing a module-shaped path (Modules/, packages/, apps/) while modules.enabled is false — asks once to enable it; also the project/stack + task-runner detection reference.
module-management
When working within any module under modules.rootpaths from .agent-project-settings.yml — Laravel HMVC, Symfony DDD-lite, Node monorepo, Python src/, Go internal/, or a custom path.
monorepo-workspace
Use to orient in a monorepo — which package manager, which workspaces, which task runner and its tasks — derived from the repository's own config and the runner's own listing, never guessed.