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/howar31/magi-workflow/setupnpx skills add howar31/magi-workflow --skill setupgit clone --depth 1 https://github.com/howar31/magi-workflowWhat 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 | $0.00078 | $0.01704 |
| Opus 5 | $0.00039 | $0.00852 |
| Sonnet 5 | $0.00016 | $0.00341 |
| Haiku 4.5 | $0.00008 | $0.00170 |
Grade B, and why
setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
if needed and write `$USER_CONFIG` with `chmod 644`. How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/magi:setup — onboarding wizard
You are the coordinator. Walk the user through configuring this plugin so the multi-CLI orchestration works on their machine. Be interactive and helpful — this is the user's first impression of the workflow.
0. Resolve paths
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-}"
[[ -z "$PLUGIN_ROOT" ]] && PLUGIN_ROOT="$(cd "$(dirname "$BASH_SOURCE[0]")/../.." 2>/dev/null && pwd)"
USER_CONFIG="$HOME/.config/magi-workflow/config.json"
DEFAULT_CONFIG="$PLUGIN_ROOT/config/default.json"
Verify $PLUGIN_ROOT/scripts/shared/preflight.sh exists. If not, the plugin is
installed incorrectly — tell the user and stop.
1. Subcommand handling
Inspect the arguments passed to the slash command:
--reset: delete$USER_CONFIG(after confirming with user), then run the full wizard.--recheck: skip the wizard. Run preflight only. If the user has no config yet, fall through to the full wizard.- (no flag): if
$USER_CONFIGalready exists, ask the user whether to re-run the wizard (it will overwrite). If they decline, run preflight to show current state and exit.
2. Run preflight
"$PLUGIN_ROOT/scripts/shared/preflight.sh"
Parse the JSON. The shape is:
{
"config_path": "...",
"reviewers": [
{"cli": "claude", "model": "opus", "status": "ok|skip|fail", "reason": "...", "version": "..."},
...
],
"summary": {"ok": N, "skip": M, "fail": K, "total": T}
}
Display a friendly table to the user (in output_language, default zh-TW):
| CLI | Status | Version | Notes |
|---|---|---|---|
| claude | ✅ ok | 2.x.x | available |
| gemini | ⏭️ skip | — | reason |
| codex | ✅ ok | 0.x.x | available |
If summary.ok == 0, abort with a message: at least claude must work for
this plugin to function. Suggest running claude login and re-running.
3. Reviewer roster
For each detected CLI, ask the user (via AskUserQuestion or chat) whether to enable it as a reviewer. Default selections:
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 · 177 lines · 78 tokens per session scan B 23cab34f38fa
setup is a skill published in the GitHub repository howar31/magi-workflow (2 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 1,704 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
panel-node-pack-sync
Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates. Use this whenever the orchestrator was just updated (installcomfyui (action:"selfupdate"), npm i -g comfyui-mcp, a new version in the ENVIRONMENT line), when a panel/bridge command fails in a way…
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
20-client-intake-brief-global
Use when an agency or freelancer takes on a NEW client and needs everything up front — an 11-section intake covering business overview, audience, current marketing, goals, budget, timeline, brand assets, approval process, and success criteria, written for the client to fill in and return. Trigger on 'client intake'…