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/plannpx skills add howar31/magi-workflow --skill plangit 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 | $0.00105 | $0.05565 |
| Opus 5 | $0.00053 | $0.02782 |
| Sonnet 5 | $0.00021 | $0.01113 |
| Haiku 4.5 | $0.00011 | $0.00556 |
Grade A, and why
plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/magi:plan — smart dispatcher + feature planning
Note:
/magi:plancreates plan documents (PLAN.md / SPEC.md / TICKET.md / HOTFIX.md) as artifacts in a sprint folder. It is NOT Claude's native plan mode (/plan). If you want an interactive read-only exploration session before formalizing a plan, use Claude's built-in/plancommand first, then run/magi:planto capture the result as a structured document.
You are the coordinator (Opus). Classify the user's request, route to the appropriate artifact, and pause for user confirmation. You do not write production code in this skill.
0. Preflight
PLUGIN_ROOT="${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"
If $USER_CONFIG is missing, tell the user to run /magi:setup first.
0.4. State preflight + init detection
Run scripts/shared/detect-state.sh. /magi:plan is allowed in any
state (it's how users start work), but check for two early-exit signals:
STATE_JSON=$(bash "$PLUGIN_ROOT/scripts/shared/detect-state.sh")
state=$(jq -r .state <<<"$STATE_JSON")
-
state=BOOTSTRAP (no root CLAUDE/README/SPEC at all) → warn the user:
Project has not been bootstrapped yet. Run
/magi:initfirst to scaffold root docs andmagi/PRD.md/magi/TECHSTACK.mdso plans have project context. Continue anyway? (y/n)If they say no → exit and let them run
/magi:init. If yes → proceed with whatever inline context they supply. -
state=INITIALIZED but
magi/PRD.mdormagi/TECHSTACK.mdmissing → same as before (existing §2 prompt to set them up).
0.5. Backlog awareness (only when no description argument was given)
If the user invoked /magi:plan without a description argument (and
without an explicit slug+description form), check for magi/BACKLOG.md:
[[ -f magi/BACKLOG.md ]] && pending=$(awk '/^## Pending/{flag=1;next} /^## /{flag=0} flag && /^- \[ \]/' magi/BACKLOG.md)
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.
- 2d ago First seen · 523 lines · 105 tokens per session scan A c5ee07daa529
plan is a skill published in the GitHub repository howar31/magi-workflow (2 stars, last pushed 3d ago), licensed MIT. It adds 105 tokens to every session and 5,565 once invoked, about $0.0005 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 skills, from other repositories
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.
comfyui-node-registry
Authoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec, comfy-cli publishing, and CI.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
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).
chief-strategy-officer
Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…
performance-analysis
Measurement approaches, profiling patterns, bottleneck identification, and optimization guidance. Use when diagnosing performance issues, establishing baselines, identifying bottlenecks, or planning for scale. Always measure before optimizing.