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/tasksnpx skills add howar31/magi-workflow --skill tasksgit 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 | $0.00058 | $0.01467 |
| Opus 5 | $0.00029 | $0.00733 |
| Sonnet 5 | $0.00012 | $0.00293 |
| Haiku 4.5 | $0.00006 | $0.00147 |
Grade A, and why
tasks scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/magi:tasks — milestone & task decomposition
You are the coordinator (Opus). Convert a confirmed PLAN.md or SPEC.md into a TASKS.md, then stop and wait for user confirmation. You do not write production code in this skill.
0. Preflight
PLUGIN_ROOT="${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 $USER_CONFIG is missing, tell the user to run /magi:setup first.
0.5. State preflight (auto-refuse if not allowed)
Run scripts/shared/detect-state.sh and check whether tasks is in
the disallowed_skills map. If yes, present the reason + suggested next
step in the user's output_language and abort.
STATE_JSON=$(bash "$PLUGIN_ROOT/scripts/shared/detect-state.sh")
blocked=$(jq -r '.disallowed_skills["tasks"] // empty' <<<"$STATE_JSON")
if [[ -n "$blocked" ]]; then
reason=$(jq -r '.disallowed_skills["tasks"].reason' <<<"$STATE_JSON")
suggest=$(jq -r '.disallowed_skills["tasks"].suggest' <<<"$STATE_JSON")
echo "Cannot run /magi:tasks: $reason"
echo "Suggested: $suggest"
exit 1
fi
After preflight passes, also surface any staleness warnings relevant
to this skill. For /magi:tasks, watch for stale_plan_review (the
review ran before the latest PLAN edit). If present, ask the user
whether to re-run /magi:review-plan first or proceed anyway. Default
proceed if the user just hits Enter.
--force skips the entire preflight (advanced/recovery only).
1. Locate the sprint
Find the target magi/<num>-<slug>/ folder:
- If user passed an argument (
/magi:tasks 03-profile-page), use it. - Otherwise, list
magi/*/folders sorted by<num>desc and ask the user to pick. Default to the most recent.
Read the existing PLAN.md or SPEC.md in the chosen folder. If neither
exists, tell the user to run /magi:plan first.
2. Read context
magi/PRD.md,magi/TECHSTACK.md(project-level)CLAUDE.md,AGENTS.md(root)- The PLAN/SPEC for the current sprint
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 · 151 lines · 58 tokens per session scan A 61c74bcb3be1
tasks is a skill published in the GitHub repository howar31/magi-workflow (2 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 1,467 once invoked, about $0.0003 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.