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 commands/mooreslaws/expert-mind-skill/initgit clone --depth 1 https://github.com/mooreslaws/expert-mind-skillWhat 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 | $0.00015 | $0.03162 |
| Opus 5 | $0.00008 | $0.01581 |
| Sonnet 5 | $0.00003 | $0.00632 |
| Haiku 4.5 | $0.00002 | $0.00316 |
Grade A, and why
init scanned grade A 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Validate via curl: How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Mind Skill — Setup Wizard
This wizard is stateful via filesystem inspection and never blocks.
At every step the user can pick "I'm done for now" and walk away — anything
left undone can be filled in by re-running /expert-mind-skill:init later.
Step 0 — Inspect current state
Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/wizard_state.py (without --json)
in the user's CWD. Show the user the output verbatim — it's the dashboard.
Then read JSON form: python3 ${CLAUDE_PLUGIN_ROOT}/scripts/wizard_state.py --json
and parse to drive decisions below. The JSON includes a top-level
_pipeline_ready boolean and _blockers list — use them to phrase choices.
Example output the user sees:
Setup state:
✅ LLM provider done (needed for /run) [provider=anthropic]
⚪ Personas pending (needed for /run) none active yet; 15 presets available
✅ Apify token done (needed for /run) token ends in …xxxx
➖ readwise creds skipped (optional)
⚪ Cron schedule pending (optional)
⚪ First run pending (optional)
⚪ Pipeline not yet runnable. Blockers:
- no personas configured yet (add at least one)
You can exit the wizard anytime — these can be filled in later.
Status legend:
✅ done— step is complete⚪ pending— not done; user may fill in now or any time later➖ skipped— not applicable to this user's config (auto-detected)❌ error— something is wrong (e.g. invalid API key)
(needed for /run) vs (optional) describes what gates the pipeline,
NOT what the wizard requires. Pipeline running and wizard completing are
different concepts — wizard always lets the user exit.
Step 0.5 — Ask what to do next
After showing the dashboard, use AskUserQuestion. Phrase the "resume" option
adaptively based on what _blockers says (if no blockers, recommend Cron or
First run; if blockers exist, recommend resolving them).
"What would you like to do?"
Options:
- Continue setup — wizard picks the first pending step and walks through it
- Pick a specific step — multi-pick from the 5 steps below (any combination, including re-doing a done step)
- I'm done for now — exit. If
_pipeline_readyis True, run/expert-mind-skill:runto do the first pull, or wait for cron. If False, the user knows which blockers to fix later - Start over — re-run wizard from Step 1 (existing personas/.env are preserved unless explicitly overwritten)
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.
- 3d ago First seen · 303 lines · 15 tokens per session scan A 56e83659f2c6
init is a command published in the GitHub repository mooreslaws/expert-mind-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 3,162 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
auto-mode
Idea-to-running-code lifecycle orchestration. 10-phase pipeline with 5 hard decision gates, wave-based parallelism, and STATE.json resumability. Composes /deep-research, /auto-swarm-nth, /production-upgrade, /security-audit, and /ship into a single end-to-end flow.
max-research
Nuclear-scale autonomous research — deploys 500-1000 agents in ONE massive simultaneous wave for exhaustive topic saturation. Deep-research methodology × auto-swarm scale = maximum parallel intelligence. WARNING: Extreme resource consumption.
omni-plan
ProductionOS flagship — 13-step orchestrative pipeline with tri-tiered evaluation, recursive convergence, CEO/Eng/Design review chain, CLEAR framework evaluation, multi-model judge tribunal, and autonomous PIVOT/REFINE/PROCEED decisions. Targets 100% production-ready output.
auto-swarm-nth
Nth-iteration agent swarm — spawns parallel agent waves, evaluates strictly per wave, re-swarms gaps until 100% coverage and 10/10 quality. Can invoke any ProductionOS skill or command within waves.
frontend-upgrade
Full-stack frontend upgrade pipeline — fuses /production-upgrade iterative audit with /plan-ceo-review vision and /plan-eng-review rigor. Deploys parallel auto-swarm agents for iterative audit and execution. Enriched with /deep-research for competitive parity.
omni-plan-nth
Nth-iteration omni-plan — recursive orchestration that chains ALL ProductionOS skills and agents, evaluates strictly per iteration, and loops until 10/10 is achieved. Each iteration can invoke any command or skill in the system.