01 · PROSPECTOR
Finds the relevant files and lines.
17 tools · 7 search · tome trio
MULTI-AGENT ORCHESTRATION
Forge code with a six-agent crew.
Plans before it builds. Reviews its plans. Verifies its own work. A dual-harness extension for the pi and prime coding agents.
# Plan
Status: done
## Steps
- [x] 1. Add assertFiniteNumber() helper in src/validate.js
- [x] 2. Gate add()/div() args in src/calc.js
- [x] 3. Gate fmt() in src/format.js
- [x] 4. Add "test" script to package.json
- [x] 5. Add test/index.test.js covering happy + error paths
## Adversarial Reviews
### APPROVE (2026-06-24T15:58:51Z)
Verified prospector's findings against disk. Plan below. …
VERDICT: approve
## Verification
### APPROVE (2026-06-24T15:59:02Z)
All steps done, tests pass, no type errors.
VERDICT: APPROVE.smithy/plan.md — cat it any time.
THE WORKFLOW
The forge line
Every /smithy run is a
workflow, not a free-for-all. Scroll — the spark walks the line.
02 · DRAFTSMAN
Produces the plan.
16 tools · 6 search · tome trio
03 · INSPECTOR
Fresh-instance adversarial review of draftsman's plan.
16 tools · 6 search · tome trio
04 · SMITH
Builds.
24 tools · edit · write · bash
05 · JUDGE
Verifies smith's work against the plan (runs tests/type-checks).
22 tools · 7 search · bash · tome trio
WHAT SETS IT APART
Why it's different
Most agent harnesses hand a single model a single toolset and say "go." smithy-agent runs a disciplined workflow and keeps the receipts.
A plan you can actually see
Every plan, adversarial critique, and judge verdict persists to .smithy/plan.md — a human-readable ledger that survives restarts. Read it mid-run, diff it, grep it.
Plans get stress-tested first
Non-trivial plans are auto-reviewed by inspector — a fresh-instance critic — before anything builds.
Work gets verified, not just produced
judge runs your test suite and type-checker and won't APPROVE until they pass.
It won't spiral
A thrash detector disengages on stalls and repeats; an echo-loop guard stops the model replying to its own subagent's stream. Autonomous runs stay sane.
Hard budgets
Every run accepts a { tokens?, usd? } ceiling. Hit it and the loop stops cleanly with [DONE:budget] — no surprise invoices, no half-finished plans.
Optional code-graph memory
Register smithy-mcp-bridge and every agent gets tome — a code-graph server behind three tools (tome_search / tome_describe / tome_call). Agents query the graph when the bridge is up and fall back to grep when it isn't.