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 laurigates/claude-plugins --skill comfy-cligit clone --depth 1 https://github.com/laurigates/claude-pluginsWrote 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/laurigates/claude-plugins/comfy-cli)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/comfy-cli"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfy-cli/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/laurigates/claude-plugins/comfy-cli"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfy-cli.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 | $0.00058 | $0.01386 |
| Opus 5.5 | $0.00023 | $0.00554 |
| Sonnet 5.5 | $0.00012 | $0.00277 |
| Haiku 4.5 | $0.00006 | $0.00139 |
Grade B, and why
comfy-cli scanned grade B 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| `comfy launch [--background]` | Spawns a second ComfyUI process competing for port 8188 and the GPU against the systemd unit. Use `sudo systemctl start/stop comfyui.service` instead — the project `CLAUDE.md` covers thi How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
comfy CLI on this install
comfy (comfy-cli) is the upstream Comfy Org Python CLI. Installed here via
uv tool at ~/.local/share/uv/tools/comfy-cli/ (binary symlink at
~/.local/bin/comfy). The default workspace is already pinned to
your ComfyUI install's root — never pass --workspace, never run set-default once it's pinned.
The service runs via systemd on 0.0.0.0:8188 (see project CLAUDE.md). The
CLI's lifecycle commands assume it owns the process. Most don't apply here.
The useful surface is custom-node management, headless API execution,
and snapshots. Almost everything else is either a no-op or actively
conflicts with the systemd unit.
When to Use This Skill
| Use this skill when... | Use instead when... |
|---|---|
The user asks to use the comfy CLI - install/update/bisect nodes, snapshot/restore, publish, run workflows headlessly |
Managing custom nodes via the ComfyUI-Manager UI directly |
Running a workflow via comfy run --workflow ... --port ... |
Running headlessly over the raw HTTP API -> comfyui-pack-live-smoke |
What to use
| Task | Command |
|---|---|
| List installed custom nodes | comfy node simple-show installed |
| Install a custom node by registry name | comfy node install <name> |
| Install a node directly from the comfy registry by ID (use when Manager's curated list lags or the node was just published) | comfy node registry-install <node-id> |
| Install all custom nodes referenced by an imported workflow | comfy node install-deps --workflow path/to/workflow.json |
| Update one or more nodes | comfy node update <name> [<name> ...] |
| Update every custom node + Comfy core | comfy node update all |
Reinstall a node's requirements.txt (after a venv rebuild or import error) |
comfy node fix <name> |
| Snapshot current node state to JSON | comfy node save-snapshot --output snapshots/$(date -I).json |
| Restore a snapshot | comfy node restore-snapshot snapshots/<file>.json |
| Bisect which custom node is breaking startup | comfy node bisect start then good/bad |
| Generate a dep manifest for a workflow you're sharing | comfy node deps-in-workflow --workflow X.json --output X.deps.json |
| Run an API-format workflow against the running server | comfy run --workflow path.json --port 8188 --timeout 600 --verbose |
| Show installed models in a table | comfy model list |
| Inspect workspace / running-server state | comfy which, comfy env |
What ships with it
2 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.
- 12d ago Changed · -257 lines scan D → B 14862a51f56e
- 1mo ago First seen · 333 lines · 58 tokens per session scan D fced8b85cbc3
comfy-cli is a skill published in the GitHub repository laurigates/claude-plugins (60 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,386 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
changelog-summarizing
Use this skill when the user asks to summarize, recap, or post about repository changes in the Shopware AI Coding Tools marketplace since a given date — phrases like "write a changelog post for Discord", "recap this week's commits for Slack", "summarize what shipped since 2026-04-01", "draft a release announcement".…
commit-message-writing
Use this skill when the user explicitly asks to generate, write, draft, or create a commit message, squash commit, commit title, or merge commit message for the Shopware core repository (shopware/shopware). Supports two modes — full commit messages (title + body) for branch commits, and squash merge titles…
morning-brief
Operator's read-only morning view of the current GitHub repo in one pass: open counts per queue label, merge-ready PRs, parked decisions with their RECOMMENDED lines, loop-lane telemetry freshness, and per CI lane the week's failures by class, limit stops, restarts and turn headroom, and model usage per activity and…
realign-file-names
Apply a file-name rename plan one file at a time, one human acceptance each: git mv, rewrite only the reference shapes each citing file's tier allows, rebuild generated records, and sweep for stragglers. Refuses a blanket yes, a range, a glob, and 'all'. Use when: 'apply the rename plan', 'apply FN-...', 'do the docs…
feature-branch-pr-writing
Use this skill when the user asks to write, draft, create, or improve a PR description for a Shopware core repository PR — AND that PR targets a non-trunk feature branch (not trunk itself). Trigger phrases like "write a PR description", "draft the PR", "what should I put in the PR body". The skill detects the target…
issue-analyzing
Use this skill when the user asks to analyze a specific GitHub issue, understand what area of code an issue affects, assess an issue's scope, or research the code context around an issue — example triggers like "analyze issue.