workflow
Multi-agent workflow (prospector → draftsman → inspector → smith → judge). Collaborative.
REFERENCE
Commands
All commands run inside the pi or prime-agent TUI once the smithy-core extension is registered. Commands colliding with prime built-ins (/usage, /context, /goal) register as /smithy-usage, /smithy-context, /smithy-goal there.
Workflow
The multi-agent pipeline — collaborative (/smithy, you approve), autonomous (/smithy-auto, hands-off), or quest-driven.
workflow
Same workflow, fully autonomous — no approval gates. Hard 25-turn ceiling (override with SMITHY_AUTO_MAX_TURNS) — runaway-run backstop, not a token budget.
workflow
Force sequential (no parallel members).
workflow
Cap parallel members at N.
Planning
Plan with prospector/draftsman/inspector; approve, revise, or cancel in plain prose.
planning
Plan-only mode: the model interviews you, then drives prospector → draftsman → inspector via task(). No markers — you approve or revise in plain prose.
Inspection
Review plans, verify work, and inspect what smithy loaded.
inspection
Show the AGENTS.md / CLAUDE.md files smithy loaded for this turn.
inspection
Show the rule files smithy loaded for this session. Pass 'full' to include content.
inspection
Show the Claude Code configs smithy loaded for this session. Pass 'full' to include raw content.
inspection
Show loaded Claude Code hooks; pass "on" to enable (env-gated).
Meta
Inspect smithy state: checkpoints, compaction, agents, goals, todos, and the ledger.
meta
Inspect smithy state (model, loops, sessions).
meta
Reload SMITHY_AGENT_THINKING* env overrides into the live session.
meta
Show current token/cost usage.
meta
Show bash timeout policy and statistics.
meta
Show compaction config and statistics, or tune: /compaction config toolResultMaxBytes <N>.
meta
Show the current todo list.
meta
Create a git checkpoint now (without waiting for next turn).
meta
List recent git checkpoints in this session.
meta
List available agents (scout, draft, smith, judge, +user-defined).
meta
Re-scan the user and project agents directories.
meta
Show or add/remove user-level allow/deny rules for tools.
meta
Manage per-path tool scopes. Subcommands: list, add, remove.
meta
Manage user goals. Subcommands: list, add, done, cancel, remove.
meta
Show ember state and unfinished todo count, or force-disengage with /ember off.
meta
Pull latest from origin and rebuild if a build script exists (no-op otherwise).
meta
Walk the repo and generate AGENTS.md scaffolding at each directory.
Quest loop
/smithy-quest onlyQuest-only commands used by the autonomous /smithy-quest loop, not the core /smithy workflow. The quest loop runs repeatedly — the parent model orchestrates prospector→draftsman→inspector→smith→judge→questmaster until the questmaster decides the goal is met, a backstop fires, or a user-supplied predicate passes.
Goal-driven autonomous LOOP (model-orchestrated). Repeats prospector→draftsman→inspector→smith→judge→questmaster until the goal is met, --until predicate passes, budget runs out, or --max-iters is hit. Questmaster (a fresh-instance critic) decides QUEST_COMPLETE / QUEST_CONTINUE <next focus> / QUEST_SATURATED between iterations.
Every smithy slash command registered through
pi.registerCommand,
grouped by surface. Click any signature to copy it.
Legacy: /smithy_loop and its alias
/ulw still dispatch but emit a
one-time deprecation notice pointing to
/smithy (collaborative) or
/smithy-auto (autonomous). For
parallel fan-out, use
/smithy --concurrency=N or
--sequential.