init

A step-by-step setup wizard for configuring the add-on. It checks the current filesystem state, shows what is done or missing, and can be stopped and resumed later.

In plain words
What is it for?
Use it to configure the language-model provider, personas, source credentials, schedules, and the first pipeline run.
Why use it?
It makes an incomplete installation understandable and lets you configure only what is needed. You can leave optional steps unfinished without losing the progress already made.

Command

Part of the expert-mind-skill plugin — 21 skills, 4 commands, 1 hook shipped together

Install

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.

agentmods
npx agentmods add commands/mooreslaws/expert-mind-skill/init
Clone the repo
git clone --depth 1 https://github.com/mooreslaws/expert-mind-skill

Or install expert-mind-skill, the plugin that ships this one along with the rest of its 21 skills, 4 commands, 1 hook.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,162 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 56e83659f2c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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:
commands/init.md · 303 lines

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_ready is True, run /expert-mind-skill:run to 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)

Read the full file on GitHub · 303 lines

Changes

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.

  1. 3d ago First seen · 303 lines · 15 tokens per session scan A 56e83659f2c6

Subscribe to this mod's changes

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.

Related

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.

ShaheerKhawaja/ProductionOS · 68 tokens

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.

ShaheerKhawaja/ProductionOS · 48 tokens

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.

ShaheerKhawaja/ProductionOS · 62 tokens

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.

ShaheerKhawaja/ProductionOS · 51 tokens

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.

ShaheerKhawaja/ProductionOS · 56 tokens

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.

ShaheerKhawaja/ProductionOS · 51 tokens